AchillesChen

huggingface上下载的Qwen3-VL官方模型可以直接在沐曦卡上通过vllm运行吗，沐曦GPU兼容吗

huggingface上下载的Qwen3-VL官方模型可以直接在沐曦卡上通过vllm运行吗，沐曦GPU兼容吗

vllm-metax:0.11.0-maca.ai3.3.0.11-torch2.6-py310-ubuntu22.04-amd64 能够提供该镜像的离线包下载？
本人在公司内网开发无法docker pull拉取镜像，能否提供离线下载方式？

还有想请问一下，沐曦推理框架的vllm方式是否适配了Qwen2.5-VL或者Qwen3-VL模型？

因为工作原因，需要在内网网络隔离环境下，部署hunyuanOCR模型。我下载了vllm-metax:0.10.2-maca.ai3.2.1.7-torch2.6-py310-centos9-amd64镜像，并执行vllm serve /models/hunyuanOCR/ --no-enable-prefix-caching --mm-processor-cache-gb 0 --gpu-memory-utilization 0.2命令。

报错信息如下：
(APIServer pid=810)
pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
(APIServer pid=810) Value error, The checkpoint you are trying to load has model type 'hunyuan_vl' but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
(APIServer pid=810)
You can update Transformers with the command 'pip install --upgrade transformers'. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command 'pip install --git+github.com/huggingface/transformers.git [type=value_error, input_value=ArgsKwargs((), {'model':...recessor_plugin':None})

请问是该镜像的transformers库版本过低吗，应该下载哪个镜像呢？