From c3c6373460962941a60bc0ba1e6b6bb92dd99bdf Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 19:49:52 +0000 Subject: [PATCH] state: generation 11665 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 80 +-- .modelhub_state/outcome_checkpoint.json | 621 +++++++++--------- .modelhub_state/recent_outcomes.jsonl | 12 +- .modelhub_state/recovery_intents.jsonl | 1 + manifest.json | 20 +- outcomes/submissions.jsonl | 18 +- 8 files changed, 367 insertions(+), 389 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index e14c8949f..58aa5361c 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -2768,7 +2768,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-21T19:45:40.508384+00:00", + "generatedAt": "2026-09-21T19:49:38.240370+00:00", "summary": { "activeBlockCount": 139, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index f90247c34..5beef5e24 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -434,7 +434,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-21T19:48:35.760922+00:00", + "generatedAt": "2026-09-21T19:49:51.647815+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index db026b92f..f87e596a3 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-21T19:48:35.760922+00:00", + "catalogUpdatedAt": "2026-09-21T19:49:51.647815+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-21T19:48:35.760922+00:00", + "generatedAt": "2026-09-21T19:49:51.956887+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -1731,6 +1731,14 @@ ], "updatedAt": "2026-09-21T19:05:31.486227+00:00" }, + "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed|2026-09-17T13:39:53+00:00|Cambricon_mlu-370-x8": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-21T19:49:51.912478+00:00" + }, "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed|2026-09-17T13:39:53+00:00|Iluvatar_bi-150": { "taskTypes": [ "asr", @@ -1843,6 +1851,14 @@ ], "updatedAt": "2026-09-21T19:05:30.559282+00:00" }, + "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed|2026-09-17T14:05:32+00:00|Cambricon_mlu-370-x8": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-21T19:49:51.911130+00:00" + }, "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed|2026-09-17T14:05:32+00:00|Iluvatar_bi-150": { "taskTypes": [ "asr", @@ -1902,27 +1918,6 @@ ], "updatedAt": "2026-09-21T18:49:56.168757+00:00" }, - "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4|2026-08-26T16:45:23+00:00|Ascend_910-b4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:54.596970+00:00" - }, - "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4|2026-08-26T16:45:23+00:00|Iluvatar_bi-150": { - "taskTypes": [ - "asr", - "question_answering", - "reinforcement_learning", - "text-generation", - "text-to-image-generation", - "text_classification", - "vision_classification", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:54.627442+00:00" - }, "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4|2026-08-26T15:57:06+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -2003,27 +1998,6 @@ ], "updatedAt": "2026-09-21T18:49:56.062944+00:00" }, - "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT|2026-08-26T16:48:25+00:00|Ascend_910-b3": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:54.616347+00:00" - }, - "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT|2026-08-26T16:48:25+00:00|Iluvatar_bi-150": { - "taskTypes": [ - "asr", - "question_answering", - "reinforcement_learning", - "text-generation", - "text-to-image-generation", - "text_classification", - "vision_classification", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:54.649488+00:00" - }, "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT|2026-08-26T16:48:25+00:00|hygon_k100-ai": { "taskTypes": [ "text-generation", @@ -2609,6 +2583,14 @@ ], "updatedAt": "2026-09-21T19:05:25.099915+00:00" }, + "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|Cambricon_mlu-370-x8": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-21T19:49:51.871844+00:00" + }, "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|Iluvatar_bi-150": { "taskTypes": [ "asr", @@ -2850,6 +2832,14 @@ ], "updatedAt": "2026-09-21T19:05:34.814324+00:00" }, + "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit|2026-09-16T17:07:54+00:00|Cambricon_mlu-370-x8": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-21T19:49:51.956887+00:00" + }, "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit|2026-09-16T17:07:54+00:00|Iluvatar_bi-150": { "taskTypes": [ "asr", @@ -6896,6 +6886,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-21T19:48:35.760922+00:00", + "taskTreeUpdatedAt": "2026-09-21T19:49:51.647815+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index da12e738f..a20e35114 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-21T19:45:40.393452+00:00", - "lastSyncTime": "2026-09-21T19:45:40.057926+00:00", + "generatedAt": "2026-09-21T19:49:38.160009+00:00", + "lastSyncTime": "2026-09-21T19:49:37.657161+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -3077,13 +3077,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 24, "failureBreakdown": { - "ambiguous_runtime": 43, + "ambiguous_runtime": 45, "framework_architecture_unsupported": 23, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 6 }, - "failureCount": 74, + "failureCount": 76, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -3093,8 +3093,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 74, - "unresolvedFailureCount": 49 + "total": 76, + "unresolvedFailureCount": 51 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 204, @@ -3422,12 +3422,12 @@ "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { - "ambiguous_runtime": 8, + "ambiguous_runtime": 10, "framework_architecture_unsupported": 4, "model_load": 2, "参数/模板问题": 4 }, - "failureCount": 18, + "failureCount": 20, "failureRate": 1.0, "framework": "vllm-customized", "pendingCount": 0, @@ -3437,8 +3437,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 18, - "unresolvedFailureCount": 12 + "total": 20, + "unresolvedFailureCount": 14 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "attributableFailureCount": 13, @@ -3471,12 +3471,12 @@ "decisionSuccessRate": 0.0, "decisionTotal": 19, "failureBreakdown": { - "ambiguous_runtime": 18, + "ambiguous_runtime": 19, "framework_architecture_unsupported": 18, "memory_capacity": 1, "参数/模板问题": 12 }, - "failureCount": 49, + "failureCount": 50, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, @@ -3486,8 +3486,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 49, - "unresolvedFailureCount": 30 + "total": 50, + "unresolvedFailureCount": 31 }, "Iluvatar_bi-100|transformers|text-generation": { "attributableFailureCount": 0, @@ -4401,10 +4401,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 110, + "ambiguous_runtime": 111, "参数/模板问题": 3 }, - "failureCount": 113, + "failureCount": 114, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -4414,8 +4414,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 113, - "unresolvedFailureCount": 113 + "total": 114, + "unresolvedFailureCount": 114 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 17, @@ -5426,7 +5426,7 @@ "decisionSuccessRate": 0.0242, "decisionTotal": 3629, "failureBreakdown": { - "ambiguous_runtime": 1496, + "ambiguous_runtime": 1497, "architecture_compatibility": 112, "attention_backend": 1, "backend_operator": 84, @@ -5440,15 +5440,15 @@ "tokenizer_compatibility": 412, "参数/模板问题": 46 }, - "failureCount": 5948, + "failureCount": 5949, "failureRate": 0.9854, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 865, "successCount": 88, "successRate": 0.0146, - "total": 6036, - "unresolvedFailureCount": 1542 + "total": 6037, + "unresolvedFailureCount": 1543 }, "vllm-customized": { "attributableFailureCount": 6, @@ -5456,20 +5456,20 @@ "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { - "ambiguous_runtime": 8, + "ambiguous_runtime": 10, "framework_architecture_unsupported": 4, "model_load": 2, "参数/模板问题": 4 }, - "failureCount": 18, + "failureCount": 20, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, - "total": 18, - "unresolvedFailureCount": 12 + "total": 20, + "unresolvedFailureCount": 14 }, "vllm-mlu": { "attributableFailureCount": 21, @@ -5547,7 +5547,7 @@ "decisionSuccessRate": 0.0391, "decisionTotal": 128, "failureBreakdown": { - "ambiguous_runtime": 196, + "ambiguous_runtime": 197, "backend_operator": 8, "framework_architecture_unsupported": 23, "memory_capacity": 7, @@ -5556,15 +5556,15 @@ "tokenizer_compatibility": 82, "参数/模板问题": 13 }, - "failureCount": 349, + "failureCount": 350, "failureRate": 0.9859, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 17, "successCount": 5, "successRate": 0.0141, - "total": 354, - "unresolvedFailureCount": 209 + "total": 355, + "unresolvedFailureCount": 210 }, "vllm_tokenizer_patch": { "attributableFailureCount": 74, @@ -5572,7 +5572,7 @@ "decisionSuccessRate": 0.0263, "decisionTotal": 76, "failureBreakdown": { - "ambiguous_runtime": 78, + "ambiguous_runtime": 80, "backend_operator": 1, "context_length": 3, "framework_architecture_unsupported": 63, @@ -5583,18 +5583,18 @@ "tokenizer_compatibility": 1, "参数/模板问题": 27 }, - "failureCount": 180, - "failureRate": 0.989, + "failureCount": 182, + "failureRate": 0.9891, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 2, - "successRate": 0.011, - "total": 182, - "unresolvedFailureCount": 105 + "successRate": 0.0109, + "total": 184, + "unresolvedFailureCount": 107 } }, - "generatedAt": "2026-09-21T19:45:40.382485+00:00", + "generatedAt": "2026-09-21T19:49:38.148216+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 99, @@ -5628,7 +5628,7 @@ "decisionSuccessRate": 0.1636, "decisionTotal": 385, "failureBreakdown": { - "ambiguous_runtime": 179, + "ambiguous_runtime": 181, "context_length": 1, "framework_architecture_unsupported": 178, "memory_capacity": 19, @@ -5640,15 +5640,15 @@ "日志缺失": 14, "验证失败": 175 }, - "failureCount": 960, - "failureRate": 0.9384, + "failureCount": 962, + "failureRate": 0.9385, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 63, - "successRate": 0.0616, - "total": 1023, - "unresolvedFailureCount": 636 + "successRate": 0.0615, + "total": 1025, + "unresolvedFailureCount": 638 }, "Biren_166m": { "attributableFailureCount": 186, @@ -5715,7 +5715,7 @@ "decisionSuccessRate": 0.2188, "decisionTotal": 64, "failureBreakdown": { - "ambiguous_runtime": 105, + "ambiguous_runtime": 108, "framework_architecture_unsupported": 41, "memory_capacity": 4, "model_load": 3, @@ -5723,15 +5723,15 @@ "参数/模板问题": 34, "验证失败": 22 }, - "failureCount": 211, - "failureRate": 0.9378, + "failureCount": 214, + "failureRate": 0.9386, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 14, - "successRate": 0.0622, - "total": 225, - "unresolvedFailureCount": 161 + "successRate": 0.0614, + "total": 228, + "unresolvedFailureCount": 164 }, "Iluvatar_bi-100": { "attributableFailureCount": 194, @@ -5824,7 +5824,7 @@ "decisionSuccessRate": 0.0, "decisionTotal": 19, "failureBreakdown": { - "ambiguous_runtime": 187, + "ambiguous_runtime": 188, "backend_operator": 1, "framework_architecture_unsupported": 15, "memory_capacity": 1, @@ -5833,15 +5833,15 @@ "日志缺失": 1, "验证失败": 23 }, - "failureCount": 250, + "failureCount": 251, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, - "total": 250, - "unresolvedFailureCount": 231 + "total": 251, + "unresolvedFailureCount": 232 }, "Kunlunxin_r-200-8f": { "attributableFailureCount": 0, @@ -7062,6 +7062,29 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "gemma2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -7229,9 +7252,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 6 + "ambiguous_runtime": 7 }, - "failureCount": 6, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", @@ -7243,8 +7266,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 6, - "unresolvedFailureCount": 6 + "total": 7, + "unresolvedFailureCount": 7 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 0, @@ -9577,10 +9600,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "ambiguous_runtime": 3, + "ambiguous_runtime": 4, "model_load": 1 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "lfm2", @@ -9592,8 +9615,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 3 + "total": 5, + "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, @@ -9601,9 +9624,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 3 + "ambiguous_runtime": 4 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "llama", @@ -9615,8 +9638,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": { "attributableFailureCount": 0, @@ -10562,6 +10585,29 @@ "total": 7, "unresolvedFailureCount": 7 }, + "Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "modelType": "llama", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -13814,9 +13860,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 3 + "ambiguous_runtime": 4 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", @@ -13828,8 +13874,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 0, @@ -17292,13 +17338,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 3 }, - "failureCount": 1, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", + "lastTerminalAt": "2026-09-21T19:49:37.657119+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -17306,8 +17352,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 3, + "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 0, @@ -17465,15 +17511,15 @@ "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation": { - "attributableFailureCount": 5, - "consecutiveFailures": 5, + "attributableFailureCount": 3, + "consecutiveFailures": 3, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 5, + "decisionTotal": 3, "failureBreakdown": { - "ambiguous_runtime": 7, - "framework_architecture_unsupported": 3, + "ambiguous_runtime": 9, + "framework_architecture_unsupported": 1, "model_load": 2, "参数/模板问题": 4 }, @@ -17481,7 +17527,7 @@ "failureRate": 1.0, "framework": "vllm-customized", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-09-21T19:45:40.057911+00:00", + "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -17490,7 +17536,7 @@ "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 16, - "unresolvedFailureCount": 11 + "unresolvedFailureCount": 13 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "attributableFailureCount": 0, @@ -17599,21 +17645,21 @@ "unresolvedFailureCount": 6 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": { - "attributableFailureCount": 8, - "consecutiveFailures": 8, + "attributableFailureCount": 7, + "consecutiveFailures": 7, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 8, + "decisionTotal": 7, "failureBreakdown": { - "ambiguous_runtime": 6, + "ambiguous_runtime": 5, "backend_operator": 1, - "framework_architecture_unsupported": 5, + "framework_architecture_unsupported": 4, "memory_capacity": 1, "model_load": 1, "参数/模板问题": 1 }, - "failureCount": 15, + "failureCount": 13, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastPlatformFailureAt": null, @@ -17625,8 +17671,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 15, - "unresolvedFailureCount": 7 + "total": 13, + "unresolvedFailureCount": 6 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 2, @@ -17740,13 +17786,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-09-21T19:45:40.057896+00:00", + "lastTerminalAt": "2026-09-21T19:49:37.657161+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -17754,21 +17800,20 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 2, - "consecutiveFailures": 2, + "attributableFailureCount": 1, + "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 2, + "decisionTotal": 1, "failureBreakdown": { - "framework_architecture_unsupported": 1, "repository_structure": 1 }, - "failureCount": 2, + "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -17780,7 +17825,7 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 2, + "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|unknown|text-generation": { @@ -17910,31 +17955,6 @@ "total": 9, "unresolvedFailureCount": 9 }, - "hygon_k100-ai|vllm-patch-tokenizer|text-generation": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "consecutivePlatformFailures": 0, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "framework_architecture_unsupported": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm-patch-tokenizer", - "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-09-21T14:32:55.759813+00:00", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "successCount": 0, - "successRate": 0.0, - "targetGpu": "hygon_k100-ai", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 - }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 9, "consecutiveFailures": 9, @@ -18040,7 +18060,7 @@ "total": 1, "unresolvedFailureCount": 1 }, - "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, @@ -18052,8 +18072,8 @@ "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", - "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", - "modelType": "llama", + "lastTerminalAt": "2026-09-21T19:49:37.657097+00:00", + "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -18065,6 +18085,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 2 + }, + "failureCount": 2, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "lastTerminalAt": "2026-09-21T19:49:37.657119+00:00", + "modelType": "llama", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 2, + "unresolvedFailureCount": 2 + }, "Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -18825,13 +18870,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "ambiguous_runtime": 3, + "ambiguous_runtime": 4, "model_load": 1 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", - "lastTerminalAt": "2026-09-21T10:57:20.777281+00:00", + "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, @@ -18841,8 +18886,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 3 + "total": 5, + "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, @@ -18851,12 +18896,12 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 3 + "ambiguous_runtime": 4 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", - "lastTerminalAt": "2026-09-21T15:02:24.876374+00:00", + "lastTerminalAt": "2026-09-21T19:49:37.657146+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, @@ -18866,8 +18911,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": { "attributableFailureCount": 0, @@ -18919,56 +18964,6 @@ "total": 1, "unresolvedFailureCount": 0 }, - "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|exl3": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "framework_architecture_unsupported": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm-customized", - "lastTerminalAt": "2026-09-20T22:27:36.960800+00:00", - "modelType": "qwen3_5", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "exl3", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Cambricon_mlu-370-x8", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 - }, - "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|modelopt": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "framework_architecture_unsupported": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm-customized", - "lastTerminalAt": "2026-09-21T04:51:55.164962+00:00", - "modelType": "qwen3_5", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "modelopt", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Cambricon_mlu-370-x8", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 - }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -19294,6 +19289,31 @@ "total": 7, "unresolvedFailureCount": 7 }, + "Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "lastTerminalAt": "2026-09-21T19:49:37.657133+00:00", + "modelType": "llama", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -20395,31 +20415,6 @@ "total": 1, "unresolvedFailureCount": 1 }, - "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": { - "attributableFailureCount": 0, - "consecutiveFailures": 0, - "decisionFailureRate": 0.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 0, - "failureBreakdown": { - "ambiguous_runtime": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm_0_17_0_corex_4_4_0", - "lastTerminalAt": "2026-09-20T12:01:00.670830+00:00", - "modelType": "qwen3_5_moe", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Iluvatar_bi-150", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -20496,31 +20491,6 @@ "total": 2, "unresolvedFailureCount": 1 }, - "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|zaya|none": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "framework_architecture_unsupported": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm_0_17_0_corex_4_4_0", - "lastTerminalAt": "2026-09-20T12:01:00.671056+00:00", - "modelType": "zaya", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Iluvatar_bi-150", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 - }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|aquila3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -21072,6 +21042,31 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none": { + "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": "2026-09-21T19:49:37.657161+00:00", + "modelType": "lfm2", + "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 + }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -21122,31 +21117,6 @@ "total": 1, "unresolvedFailureCount": 0 }, - "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "framework_architecture_unsupported": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm_tokenizer_patch", - "lastTerminalAt": "2026-09-21T13:58:33.470413+00:00", - "modelType": "muse_glimmer", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Kunlunxin_p-800", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 - }, "MetaX_c-500|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, @@ -21246,31 +21216,6 @@ "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 - }, - "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4|none": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "framework_architecture_unsupported": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm-patch-tokenizer", - "lastTerminalAt": "2026-09-21T14:32:55.759813+00:00", - "modelType": "gemma4", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "hygon_k100-ai", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 } }, "sizedProfileCombinationStats": { @@ -22827,6 +22772,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|32": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 32, + "modelType": "gemma2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -23193,9 +23162,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 3 + "ambiguous_runtime": 4 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, @@ -23208,8 +23177,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none|30": { "attributableFailureCount": 0, @@ -26542,9 +26511,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 29, @@ -26557,8 +26526,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2|none|30": { "attributableFailureCount": 0, @@ -26639,9 +26608,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2 + "ambiguous_runtime": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, @@ -26654,8 +26623,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none|34": { "attributableFailureCount": 0, @@ -28045,6 +28014,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors|30": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "loadSizeLog2Bucket": 30, + "modelType": "llama", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -32356,9 +32349,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, @@ -32371,8 +32364,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 0, @@ -37597,15 +37590,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16381, - "totalRecords": 16575, + "terminalRecords": 16387, + "totalRecords": 16581, "totals": { "attributableFailureCount": 5908, "decisionFailureRate": 0.862, "decisionSuccessRate": 0.138, "decisionTotal": 6854, "failureBreakdown": { - "ambiguous_runtime": 4018, + "ambiguous_runtime": 4024, "architecture_compatibility": 212, "attention_backend": 1, "backend_operator": 104, @@ -37621,31 +37614,31 @@ "日志缺失": 719, "验证失败": 674 }, - "failureCount": 15435, + "failureCount": 15441, "failureRate": 0.9423, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 925, "successCount": 946, "successRate": 0.0577, - "total": 16381, - "unresolvedFailureCount": 8602 + "total": 16387, + "unresolvedFailureCount": 8608 }, "warnings": [ "GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 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 Sunrise_pt-200-x1 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "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 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -37685,6 +37678,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 16575, + "summarizedRecords": 16581, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 12c3d18fc..5ec6bfe57 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -17,6 +17,7 @@ {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.664002+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:41+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4783202", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.663896+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:40+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920239", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.663932+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:40+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920434", "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": "2026-09-21T19:49:37.657119+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093197403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T06:25:35.859746+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995261", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T05:59:02.567443+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T05:55:34+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4968995", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T05:51:50.448464+00:00", "modelId": "BAAI/Hospitality-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T05:49:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457981", "taskType": "text-generation", "verifyResult": 1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T05:42:03.443622+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T05:29:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079933", "taskType": "text-generation", "verifyResult": -1} @@ -63,6 +64,7 @@ {"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:49:19.765032+00:00", "modelId": "BAAI/Aerospace-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:47:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457982", "taskType": "text-generation", "verifyResult": 1} {"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T02:38:57.372787+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079201", "taskType": "text-generation", "verifyResult": -1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:15:17.867390+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457986", "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-customized", "lastSyncTime": "2026-09-21T19:49:37.657075+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T01:45:52.835844+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991428", "taskType": "text-generation", "verifyResult": -1} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556193+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T01:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079972", "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": "2026-09-21T18:20:35.656980+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T00:12:58.737197+00:00", "targetGpu": "Biren_166m", "taskId": "4990141", "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", "lastSyncTime": "2026-09-21T15:54:37.859021+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T00:00:11.334848+00:00", "targetGpu": "Biren_166m", "taskId": "4989991", "taskType": "text-generation", "verifyResult": -1} @@ -74,6 +76,7 @@ {"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": "2026-09-21T16:50:30.559291+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:29:12.193862+00:00", "targetGpu": "Biren_166m", "taskId": "4988754", "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": "2026-09-21T19:05:56.949036+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:29:12.187825+00:00", "targetGpu": "Biren_166m", "taskId": "4988752", "taskType": "text-generation", "verifyResult": -1} {"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T22:20:31.465723+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:19:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4587221", "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-customized", "lastSyncTime": "2026-09-21T19:49:37.657146+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-20T20:49:19.683358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093251763}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:24:36.675557+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4987943", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443541+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "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": "2026-09-21T19:05:56.949080+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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": 2345693224}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:19:10.977747+00:00", "targetGpu": "Biren_166m", "taskId": "4987874", "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": "2026-09-21T19:05:56.949051+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22210552448, "estimatedRequiredGiB": 24.849, "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": 22234091413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 17463440388, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:blackwell", "custom_tag:a100"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 22234091413}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:15:43.553144+00:00", "targetGpu": "Biren_166m", "taskId": "4987832", "taskType": "text-generation", "verifyResult": -1} @@ -161,6 +164,7 @@ {"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", "lastSyncTime": "2026-09-21T01:08:25.664308+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251763}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:54:11.089175+00:00", "targetGpu": "Biren_166m", "taskId": "4978283", "taskType": "text-generation", "verifyResult": -1} {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T19:56:29.962428+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "taskType": "text-generation", "verifyResult": -1} {"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", "lastSyncTime": "2026-09-20T11:30:54.600461+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:23:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4523512", "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", "lastSyncTime": "2026-09-21T19:49:37.657133+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175215, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018175215}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T10:51:35.807777+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4977519", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T21:06:45.850234+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T10:32:04.275294+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4977311", "taskType": "text-generation", "verifyResult": -1} {"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": "2026-09-21T18:39:29.750872+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:57:46.890719+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4976868", "taskType": "text-generation", "verifyResult": -1} {"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", "framework": "vllm", "lastSyncTime": "2026-09-20T10:06:20.452855+00:00", "modelId": "KoboldAI/fairseq-dense-13B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079951", "taskType": "text-generation", "verifyResult": -1} @@ -254,6 +258,7 @@ {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["muse_glimmer"], "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867369+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:52.182815+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "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", "lastSyncTime": "2026-09-21T08:44:09.587529+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.352471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970443", "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", "lastSyncTime": "2026-09-20T23:08:35.573468+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.350050+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970442", "taskType": "text-generation", "verifyResult": -1} +{"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": "2026-09-21T19:49:37.657097+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.348395+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970436", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266103+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "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", "lastSyncTime": "2026-09-21T04:51:55.164906+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.344449+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "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", "lastSyncTime": "2026-09-20T22:27:36.960842+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation", "verifyResult": -1} @@ -273,6 +278,7 @@ {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902097+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.457045+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970357", "taskType": "text-generation", "verifyResult": -1} {"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": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901805+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "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:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.451794+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970348", "taskType": "text-generation", "verifyResult": -1} {"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901895+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "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:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.449495+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970352", "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": "2026-09-21T19:49:37.657161+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.441724+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970354", "taskType": "text-generation", "verifyResult": -1} {"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", "lastSyncTime": "2026-09-21T19:13:53.564431+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.974956+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970340", "taskType": "text-generation", "verifyResult": -1} {"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", "lastSyncTime": "2026-09-21T03:25:53.878060+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.934664+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970335", "taskType": "text-generation", "verifyResult": -1} {"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", "lastSyncTime": "2026-09-21T10:57:20.777339+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.904873+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970336", "taskType": "text-generation", "verifyResult": -1} @@ -292,9 +298,3 @@ {"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", "lastSyncTime": "2026-09-20T22:43:47.754882+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.813804+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970120", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T14:14:39.678925+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.801267+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970119", "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", "lastSyncTime": "2026-09-20T17:09:45.266093+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.789758+00:00", "targetGpu": "Biren_166m", "taskId": "4970118", "taskType": "text-generation", "verifyResult": -1} -{"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": ["zaya"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.671056+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.783924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970117", "taskType": "text-generation", "verifyResult": -1} -{"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": ["muse_glimmer"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T13:58:33.470413+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:29.643802+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970111", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.670830+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:29.635942+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970115", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-customized", "lastSyncTime": "2026-09-20T22:27:36.960800+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "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": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.651764+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970045", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-customized", "lastSyncTime": "2026-09-21T04:51:55.164962+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "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": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.636924+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970040", "taskType": "text-generation", "verifyResult": -1} -{"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": ["gemma4"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T14:32:55.759813+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "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:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.472121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970033", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 9686afea4..8fcc818df 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2276,6 +2276,7 @@ {"batchId": "77c487ce74c3435d8ab3a649afb198ab", "completedAt": "2026-09-21T19:37:12.837534+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:37:11.217733+00:00", "framework": "vllm-mlu", "intentId": "036b5b6c867b464a8dd205afa49255ab", "lastModified": "2026-09-21T18:24:35+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "reason": null, "reconciledAt": "2026-09-21T19:45:56.474803+00:00", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006369", "taskType": "text-generation"} {"batchId": "77c487ce74c3435d8ab3a649afb198ab", "completedAt": "2026-09-21T19:37:12.837537+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:37:11.217795+00:00", "framework": "vllm-mlu", "intentId": "53881eb74f5b4ec1b37f865a0ee40757", "lastModified": "2026-09-21T18:28:31+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "reason": null, "reconciledAt": "2026-09-21T19:45:56.474183+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006370", "taskType": "text-generation"} {"batchId": "77c487ce74c3435d8ab3a649afb198ab", "completedAt": "2026-09-21T19:37:12.837540+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:37:11.217856+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c39e8b19e53420794e745818fa2b66d", "lastModified": "2026-09-21T18:48:50+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "reason": null, "reconciledAt": "2026-09-21T19:45:56.478375+00:00", "repoId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation"} +{"batchId": "bd2f89ade5594cb3a4fa1b1374160b5c", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:49:52.077460+00:00", "framework": "vllm-customized", "intentId": "cf78d4eb48ba4de58804bb206289e065", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691776+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.136949+00:00", "framework": "vllm", "intentId": "cff6b666a842431faf928f94c2086fdf", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index dcd073da4..2a933b89f 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.20.2", "checksums": { ".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f", - ".modelhub_state/architecture_compatibility_blacklist.json": "2356b1e8f1db24f49498d4835636c462e21170033dbf2bb6acd6fa0289958485", + ".modelhub_state/architecture_compatibility_blacklist.json": "ce63be601c08b4a80c4e6589959baeb81298c5a6b63c945731656a93f57abbc4", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "0d395b04accafa5a6a54227cedee1139abbee38fbcb1e201576282483052aa12", - ".modelhub_state/official_capabilities.json": "a99bb10b4f0dde9f244a2078f9118a168b25337a0526b9a661ccceb8608ee8a1", - ".modelhub_state/outcome_checkpoint.json": "cf7637aacdc4c501588acf14604094f721a0422d1cc5e01184bab2b97c4d0c87", + ".modelhub_state/market_intelligence.json": "9ae722997a0e423984cd61184cae4606b86d0490278f52149d23d4ac7a282812", + ".modelhub_state/official_capabilities.json": "adbb82b4daf334ed4c6beeec7e4ebb0bb99eb2c014a0f885db1f730060cdb56a", + ".modelhub_state/outcome_checkpoint.json": "0c16dad55bbb523148961becb7bf3e8a026f45508be98fe50d3e0e78d6c039e7", ".modelhub_state/queue_cleanup_latest.json": "fab470f2bbf8c39d73c8917d9fdab78c775c47a597aa2530a529e5a7ae55d4ec", - ".modelhub_state/recent_outcomes.jsonl": "78f35d78ae937f87141b8551b278b735ff46ac1dd8e7309744ec3c3c3868a31a", + ".modelhub_state/recent_outcomes.jsonl": "0e8003011fc7ffe4b589f4c251a9a27dcc4a692e1ded9860e25289e730723bf3", ".modelhub_state/recovery_active_tasks.jsonl": "adc4df6fe1d0697ba7db3882a70cf2c5fe76e65dcb377b82814e5aeafd789c94", - ".modelhub_state/recovery_intents.jsonl": "6384f10dc39ff6be9a196d2124e276a62607cda9c845c76662420174ac0c92e9", + ".modelhub_state/recovery_intents.jsonl": "40d03d25b9afbb641cec029c083a2063b79a82572235c22bda676d9241ec3b2d", ".modelhub_state/routing_intelligence.json": "93ad575e3d114fb5633ccd1450a26b636b4ae40cd8b1ac57ef541bbb1edfdc7c", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "fa750701ce66a72f48255ab2c7568f3a163cc05950dd46fb3649896782601f6e", - "outcomes/submissions.jsonl": "4eac48471d22799bb3e2ce8e78bc5c8ec2c5cdc2fa3a4f2ed88c7ba51dfbdcf6" + "outcomes/submissions.jsonl": "c7cfdd42c1fe73e633bb406f7fadbba2a76f27eee7dae60e68fbfce83ea7ec31" }, - "generation": 11664, - "phase": "cycle", + "generation": 11665, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T19:48:36.254943+00:00", + "updatedAt": "2026-09-21T19:49:52.274299+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 4ad5fa7a7..a093f6fc5 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -546,7 +546,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671087+00:00", "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:57:37.936950+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970337", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671304+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663548868}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:57:37.944617+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970338", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671298+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.462403+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970353", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670960+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.441724+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970354", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671026+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "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:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.439990+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970355", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670624+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.535522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970356", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671236+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.447710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970349", "taskType": "text-generation", "verifyResult": null} @@ -554,7 +553,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671020+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:41.296912+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:04:34.964276+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367987, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:01:42.646836+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970409", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:04:34.964288+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.317909+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970439", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:04:34.964242+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.348395+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970436", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:04:34.964269+00:00", "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824831, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824831}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:02:45.354619+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970444", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901779+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.479634+00:00", "targetGpu": "Vastai_va16", "taskId": "4970501", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901761+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "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:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:09:56.489765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970500", "taskType": "text-generation", "verifyResult": null} @@ -641,7 +639,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473034+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:49:41.611337+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977491", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473061+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:49:41.634018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4977490", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473015+00:00", "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:50:01.755721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977518", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.472942+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175215, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018175215}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:51:35.807777+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4977519", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552434+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:19:51.535102+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977812", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552425+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:19:51.641136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977829", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552441+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:20:03.373586+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977833", "taskType": "text-generation", "verifyResult": null} @@ -785,7 +782,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:17:51.457586+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:15:43.284287+00:00", "targetGpu": "Biren_166m", "taskId": "4987804", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:21:25.760194+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34327989512, "estimatedRequiredGiB": 38.385, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 34346039951, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 34346039951}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:17:18.378926+00:00", "targetGpu": "Biren_166m", "taskId": "4987846", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T05:25:05.959941+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:22:47.667525+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4987928", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T05:42:03.443461+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-20T20:49:19.683358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093251763}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:24:36.675557+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4987943", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T05:42:03.443555+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:26:40.552644+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4987963", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T05:42:03.443498+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:26:57.682364+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4987965", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443590+00:00", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_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:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:28:22.564707+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4988004", "taskType": "text-generation", "verifyResult": null} @@ -834,7 +830,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295655+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "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": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:24:06.954538+00:00", "targetGpu": "Biren_166m", "taskId": "4991108", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295617+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "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": 29973200235, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "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:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973200235}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:27:07.435514+00:00", "targetGpu": "Biren_166m", "taskId": "4991159", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:54:21.980326+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:37:49.775343+00:00", "targetGpu": "Biren_166m", "taskId": "4991287", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T09:54:21.980276+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:45:52.835844+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991428", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T09:58:02.958221+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T00:42:10.765015+00:00", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 4020783717}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:54:23.239188+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991516", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:58:02.958201+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:54:23.235347+00:00", "targetGpu": "Biren_166m", "taskId": "4991515", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:01:37.498148+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:57:56.851808+00:00", "targetGpu": "Biren_166m", "taskId": "4991645", "taskType": "text-generation", "verifyResult": null} @@ -922,7 +917,6 @@ {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T13:58:33.470424+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 13.067, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 8740644030, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11692052998}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T05:42:36.743182+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4994779", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759776+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093197700}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.861357+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995262", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093197403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T06:25:35.859746+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995261", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T15:02:24.876338+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:33:09.355417+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4995337", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876266+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449487}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:49:13.744923+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4995536", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876381+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:49:41.154458+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4995549", "taskType": "text-generation", "verifyResult": null} @@ -1005,12 +999,12 @@ {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T19:45:40.057919+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261938}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:42:21.093921+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5000138", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T19:45:40.057904+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:42:38.193150+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5000196", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:45:40.057852+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:44:25.650478+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000197", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T11:15:42.052853+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:44:40.201702+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000223", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824831, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T11:15:42.052853+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 2033824831}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:46:27.062138+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000224", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:46:27.192316+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000225", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:46:27.357049+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000226", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:46:34.674727+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000249", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:48:23.283753+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000251", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657088+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T11:15:42.052853+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:44:40.201702+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000223", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657053+00:00", "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824831, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T11:15:42.052853+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 2033824831}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:46:27.062138+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000224", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657153+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:46:27.192316+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000225", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657126+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:46:27.357049+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000226", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657110+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:46:34.674727+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000249", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:49:37.657141+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:48:23.283753+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000251", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:50:46.187626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5000279", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:54:31.274098+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5000347", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4020783717}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T11:57:55.153765+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5000419", "taskType": "text-generation", "verifyResult": null}