diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 22d62349e5..878c691222 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2139,32 +2139,32 @@ {"batchId": "63129c0ae07d4bea9e9c888a456065c5", "completedAt": "2026-09-21T16:14:09.825813+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:01:05.135399+00:00", "framework": "transformers", "intentId": "0d303407ec8b4f8297cead35441f1865", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "reason": null, "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5003412", "taskType": "text-generation"} {"batchId": "63129c0ae07d4bea9e9c888a456065c5", "completedAt": "2026-09-21T16:14:09.825815+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:01:05.135459+00:00", "framework": "transformers", "intentId": "91f507a94e424fb8bf65e31552ea0da0", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5003413", "taskType": "text-generation"} {"batchId": "63129c0ae07d4bea9e9c888a456065c5", "completedAt": "2026-09-21T16:14:09.825856+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:01:05.136296+00:00", "framework": "vllm-patch-tokenizer", "intentId": "574ab131179245369797da4dbeb1077f", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "5003477", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.025912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a84892ea36a74fce931e76637685b078", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026022+00:00", "framework": "vllm_tokenizer_patch", "intentId": "79742c9612ad4ada91299c5cb0b19e49", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026068+00:00", "framework": "vllm-customized", "intentId": "8dcd71044d5749a8a1798763b35afd5e", "lastModified": "2026-08-24T20:07:32+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026133+00:00", "framework": "vllm-customized", "intentId": "a2090f76558941eaab519d7360e3916e", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026193+00:00", "framework": "vllm-customized", "intentId": "51e3db9da7974e5aa349f036a6222572", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026251+00:00", "framework": "vllm-customized", "intentId": "1dd6003f4d5044bea48b26594d7da203", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026310+00:00", "framework": "vllm-customized", "intentId": "502cca71ff6f4c53b9f12f9a52c4c1e4", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026367+00:00", "framework": "vllm-customized", "intentId": "678012b67f5440f4a2d3b42cb7a9b552", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026424+00:00", "framework": "vllm-customized", "intentId": "b891b96423e940b291f0a9090bbec397", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026482+00:00", "framework": "vllm-customized", "intentId": "5f83ab7d7a24403d9eda574fc0dfa3ed", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026539+00:00", "framework": "vllm-customized", "intentId": "1f0e8ce331ee4ffebe6fa0ad2909f50f", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026597+00:00", "framework": "vllm-customized", "intentId": "010e6010725e455cbf0a8d0ff8de85ac", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026656+00:00", "framework": "vllm-customized", "intentId": "bae91b55332d49569a09fe8955c567ca", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026720+00:00", "framework": "vllm-customized", "intentId": "47195f321bbe4b00a987c15ed43039e6", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026778+00:00", "framework": "vllm-customized", "intentId": "66ae6c6857f74d618e38158def78cb42", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026835+00:00", "framework": "vllm-customized", "intentId": "6dcb56e0480b4c0fbbd44093e75ea796", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026892+00:00", "framework": "vllm-customized", "intentId": "0618fa1328c64a76baa628027a33ccde", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026950+00:00", "framework": "vllm-customized", "intentId": "bba1a735b6494475a2df9ac32ce1cf82", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027005+00:00", "framework": "vllm-customized", "intentId": "3a2b08520d3249b8b35d050aa96708e7", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027058+00:00", "framework": "vllm-customized", "intentId": "a6d6348217cf4d2ebfee4efe01d8fa67", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027111+00:00", "framework": "vllm-customized", "intentId": "549ffcf403c6426988d1b656c94fe9f8", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027164+00:00", "framework": "vllm-customized", "intentId": "a7dbd728ea8646b4a0fd2feab9368f6c", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027216+00:00", "framework": "vllm-customized", "intentId": "1a967a56b6544a418ff853e4c7bfdcc2", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027268+00:00", "framework": "vllm", "intentId": "f700a1af5ee74960a2b656f28e6d2d98", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027327+00:00", "framework": "vllm", "intentId": "842fba2048ed4c40851a0d05130be4ef", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027384+00:00", "framework": "vllm", "intentId": "108b5d7796ff4f7eab76b1d9599f28f8", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557831+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.025912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a84892ea36a74fce931e76637685b078", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5003540", "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557883+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026539+00:00", "framework": "vllm-customized", "intentId": "1f0e8ce331ee4ffebe6fa0ad2909f50f", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003580", "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557889+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026656+00:00", "framework": "vllm-customized", "intentId": "bae91b55332d49569a09fe8955c567ca", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003541", "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557917+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027216+00:00", "framework": "vllm-customized", "intentId": "1a967a56b6544a418ff853e4c7bfdcc2", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003581", "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557919+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027268+00:00", "framework": "vllm", "intentId": "f700a1af5ee74960a2b656f28e6d2d98", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "5003582", "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557925+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027384+00:00", "framework": "vllm", "intentId": "108b5d7796ff4f7eab76b1d9599f28f8", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557922+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027327+00:00", "framework": "vllm", "intentId": "842fba2048ed4c40851a0d05130be4ef", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557914+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027164+00:00", "framework": "vllm-customized", "intentId": "a7dbd728ea8646b4a0fd2feab9368f6c", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557911+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027111+00:00", "framework": "vllm-customized", "intentId": "549ffcf403c6426988d1b656c94fe9f8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557908+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027058+00:00", "framework": "vllm-customized", "intentId": "a6d6348217cf4d2ebfee4efe01d8fa67", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557905+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.027005+00:00", "framework": "vllm-customized", "intentId": "3a2b08520d3249b8b35d050aa96708e7", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557903+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026950+00:00", "framework": "vllm-customized", "intentId": "bba1a735b6494475a2df9ac32ce1cf82", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557900+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026892+00:00", "framework": "vllm-customized", "intentId": "0618fa1328c64a76baa628027a33ccde", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557897+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026835+00:00", "framework": "vllm-customized", "intentId": "6dcb56e0480b4c0fbbd44093e75ea796", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557894+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026778+00:00", "framework": "vllm-customized", "intentId": "66ae6c6857f74d618e38158def78cb42", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557891+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026720+00:00", "framework": "vllm-customized", "intentId": "47195f321bbe4b00a987c15ed43039e6", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557886+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026597+00:00", "framework": "vllm-customized", "intentId": "010e6010725e455cbf0a8d0ff8de85ac", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557881+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026482+00:00", "framework": "vllm-customized", "intentId": "5f83ab7d7a24403d9eda574fc0dfa3ed", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557878+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026424+00:00", "framework": "vllm-customized", "intentId": "b891b96423e940b291f0a9090bbec397", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557875+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026367+00:00", "framework": "vllm-customized", "intentId": "678012b67f5440f4a2d3b42cb7a9b552", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557872+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026310+00:00", "framework": "vllm-customized", "intentId": "502cca71ff6f4c53b9f12f9a52c4c1e4", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557869+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026251+00:00", "framework": "vllm-customized", "intentId": "1dd6003f4d5044bea48b26594d7da203", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557866+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026193+00:00", "framework": "vllm-customized", "intentId": "51e3db9da7974e5aa349f036a6222572", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557863+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026133+00:00", "framework": "vllm-customized", "intentId": "a2090f76558941eaab519d7360e3916e", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557860+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026068+00:00", "framework": "vllm-customized", "intentId": "8dcd71044d5749a8a1798763b35afd5e", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "c956f7e6ac8c4127aab7bbb76129249f", "completedAt": "2026-09-21T16:19:49.557851+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:14:18.026022+00:00", "framework": "vllm_tokenizer_patch", "intentId": "79742c9612ad4ada91299c5cb0b19e49", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "63129c0ae07d4bea9e9c888a456065c5", "completedAt": "2026-09-21T16:14:09.825900+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:01:05.137048+00:00", "framework": "vllm_tokenizer_patch", "intentId": "df370c80523542e6aa6b323f023c526b", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "63129c0ae07d4bea9e9c888a456065c5", "completedAt": "2026-09-21T16:14:09.825898+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:01:05.137009+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63575d7a54884f608db844022e4d3e0c", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "63129c0ae07d4bea9e9c888a456065c5", "completedAt": "2026-09-21T16:14:09.825895+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:01:05.136970+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e49f6bd2c63b40bc8c4fd16e3bcf781f", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} @@ -2444,24 +2444,3 @@ {"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541129+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.040093+00:00", "framework": "transformers", "intentId": "2d581a4074464ac9b32bdc4d3bd68811", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541127+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.040032+00:00", "framework": "transformers", "intentId": "acd5d5693cae4892bb39f37f5b894f48", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541124+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039972+00:00", "framework": "transformers", "intentId": "5d5d3ade045047949d6556194b93586f", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541121+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039911+00:00", "framework": "transformers", "intentId": "6a04807b7a794bd6900db00983fe38bc", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541118+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039843+00:00", "framework": "transformers", "intentId": "f5bf5afd308d4ba1bac711236cf57004", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541116+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039782+00:00", "framework": "transformers", "intentId": "df2bf711918c45b8aabe7ae5274071d6", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541113+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039721+00:00", "framework": "transformers", "intentId": "4c56ccc602864a7a97813ba3930e20f9", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541110+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039653+00:00", "framework": "transformers", "intentId": "2223a6d26003465bae477a03f60e8808", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541108+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039589+00:00", "framework": "transformers", "intentId": "5733bcc2102b49c7974d72e8d2505d3a", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541103+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039503+00:00", "framework": "vllm_fix_tokenizer", "intentId": "768d2e895d4a4cd1ae2783551d54d774", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541100+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039460+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d581b508047a44d0932a907bdf99f168", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541097+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039418+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e5fc006fa1640719782125148bd5a87", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541094+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039376+00:00", "framework": "vllm_fix_tokenizer", "intentId": "308dd65537ed466a91aed120890f952a", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541091+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039334+00:00", "framework": "vllm_fix_tokenizer", "intentId": "726bb931e6a64cb3b81434ce5a40d3fa", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541088+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039290+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5ae5337dcfa94cffb48df2c2eb73fb07", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541085+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039247+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f06bd703ac04538964b952e3e497697", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541082+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039204+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a64f73eb7a944b1ea3bf011f2212fc32", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541080+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039155+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c198805e59f945138ace7b5ff618b797", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541076+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039113+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf443858ac104ef7a82864d9efc64374", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541073+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039071+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc1958ec5d5147db9c128e994aa8b978", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541070+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.039029+00:00", "framework": "vllm_fix_tokenizer", "intentId": "adf1db3045684f16a691ce4b6eda6ecc", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541067+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.038986+00:00", "framework": "vllm_fix_tokenizer", "intentId": "82c54c0ad31d47faa01cefdecc4cd249", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541064+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.038944+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6523bdb8eaba4cc79ab3c328217a41a7", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "5e2a147540214c81835c2e8614e12a4c", "completedAt": "2026-09-21T14:24:41.541061+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:17:52.038901+00:00", "framework": "vllm_fix_tokenizer", "intentId": "11c6d37d8b2f4a3da29fe2a3657e228d", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 75a3298880..ce1fde34de 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2278 + "unified_success_first": 2283 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -12,10 +12,10 @@ "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 128, "text-generation|Cambricon_mlu-370-x4|vllm": 71, - "text-generation|Cambricon_mlu-370-x4|vllm-customized": 5, + "text-generation|Cambricon_mlu-370-x4|vllm-customized": 6, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 87, "text-generation|Cambricon_mlu-370-x8|vllm": 55, - "text-generation|Cambricon_mlu-370-x8|vllm-customized": 67, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 69, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 97, "text-generation|Iluvatar_bi-100|transformers": 20, "text-generation|Iluvatar_bi-150|llamacpp": 16, @@ -23,14 +23,14 @@ "text-generation|Iluvatar_bi-150|vllm": 9, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 102, "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 48, - "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 10, + "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 11, "text-generation|Iluvatar_mrv-100|vllm": 63, "text-generation|Kunlunxin_p-800|vllm": 59, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 183, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 87, "text-generation|MetaX_c-500|vllm": 104, "text-generation|Mthreads_s4000|llamacpp": 17, - "text-generation|Mthreads_s4000|vllm": 103, + "text-generation|Mthreads_s4000|vllm": 104, "text-generation|Sunrise_pt-200-x1|vllm": 85, "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 94, "text-generation|Vastai_va16|vllm_fix_tokenizer": 75, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 132 }, - "acceptedSinceRefresh": 2278, - "acceptedTotal": 2278, - "generatedAt": "2026-09-21T16:14:09.759039+00:00", + "acceptedSinceRefresh": 2283, + "acceptedTotal": 2283, + "generatedAt": "2026-09-21T16:19:49.489409+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 16a2528b20..a7e1db90d7 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1221,3 +1221,8 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "modelId": "XHToken/Spark-X2.5-4B", "submitTime": "2026-09-21T16:04:25.392407+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003412", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-21T16:04:25.561880+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003413", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "submitTime": "2026-09-21T16:07:44.481428+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003477", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "submitTime": "2026-09-21T16:14:19.468977+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003540", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "submitTime": "2026-09-21T16:14:19.660180+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "submitTime": "2026-09-21T16:14:31.701642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003541", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "submitTime": "2026-09-21T16:16:37.962127+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x4"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T16:16:38.115066+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5003582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} diff --git a/manifest.json b/manifest.json index 2355ccda7e..d1bae874a6 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "0ad8bae3fa1afa7ca210869b402afc058a903fdc4e2d86ace5dcbd51a06fabd1", ".modelhub_state/recent_outcomes.jsonl": "5287587f515a80b0cab742de9c1b977e27211f4f5402df3cbc1d5e80b9cea96b", ".modelhub_state/recovery_active_tasks.jsonl": "e64426b669ca109165a8f6a8d7d815b5f0970920b01450d859d6fe523b922f9f", - ".modelhub_state/recovery_intents.jsonl": "07231745c7963869698c1bec8bea5ca168dccd2b09f2327b7c190063f65c6f36", - ".modelhub_state/routing_intelligence.json": "5822dd23748239cd11f692b51de53ddd7225e9950014f9398602f1d8d89e8376", + ".modelhub_state/recovery_intents.jsonl": "3116f1ef82f539fb7ad6c5396f0a1098aaa47c6b94b97e47ea307281bbaab725", + ".modelhub_state/routing_intelligence.json": "5aac3b30c8d83b88461973730b606a1bb6ccccc53da359db663dc6d9713e3643", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "4fbf48dfe31d1a6446a00934ba405823e978715b6a8d484bbe020c8fd6c96854", - "outcomes/submissions.jsonl": "4dfdf4f808178e8b5e65f3bae11e0cd9b4460d1b82f39ecd97c19bafba3c69cd" + "ledger/submissions.jsonl": "dc677a7fb092e41c93414227db93a1133c5db35cf311dab0698ef0af5c1f8f3c", + "outcomes/submissions.jsonl": "12e50028d9d9e4afd091c3903f40e1a2975d6a6fa47441bdc0b8bda6f380d970" }, - "generation": 11546, - "phase": "intent", + "generation": 11547, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T16:14:18.223405+00:00", + "updatedAt": "2026-09-21T16:19:49.747510+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 2527849afb..6fa431e788 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1153,3 +1153,8 @@ {"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T21:06:45.850234+00:00", "modelType": "spark2_5", "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}, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:04:25.392407+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003412", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T17:24:32.660406+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:04:25.561880+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003413", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "pending", "submitTime": "2026-09-21T16:07:44.481428+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003477", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"model_load": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T04:36:00.569307+00:00", "modelType": "lfm2", "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}, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:14:19.468977+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003540", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093203965, "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", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T15:02:24.876374+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": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 9093203965}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:14:19.660180+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003580", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020349648, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022916227, "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": 4022916227}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:14:31.701642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5003541", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T16:16:37.962127+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003581", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "pending", "submitTime": "2026-09-21T16:16:38.115066+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5003582", "taskType": "text-generation", "verifyResult": null}