lxysl

Please check if the package versions are correct, ensure all instructions in readme are correctly excuted. Here are some common issues others have faced that you can refer to: #56...

This issue seems to be unclear as to the cause, I recommend you check that the versions of all packages are correct, and ensure that the files in vllm_tools are...

All the issues you encountered are due to not executing the following operations: ```bash # Backup a new weight file cp -rL VITA_ckpt/ demo_VITA_ckpt/ mv demo_VITA_ckpt/config.json demo_VITA_ckpt/origin_config.json cd ./web_demo/vllm_tools cp...

> > 有没有详细一点的web_demo推理部署流程？按readme去做，接连报错。 1、先是报 Repo is must be in the form ‘repo_name’ or namespace/repo_name......，排查是readme中“mv demo_VITA_ckpt/config.json demo_VITA_ckpt/origin_config.json”这句话把config.json去掉了，把config.json补上，问题解决。 2、然后遇到 limit_mm_per_prompt is only supported for multimodal models. 把limit_mm_per_prompt={‘image’:256, 'audio':50}注释掉，问题解决。 3、又遇到vllm中['VITAQwen2ForCausalLM'] are not supported...

The root cause of your issue is: ``` [rank0]: File "/usr/local/lib/python3.10/site-packages/vllm/model_executor/models/qwen2.py", line 959, in _validate_shape [rank0]: raise ValueError( [rank0]: ValueError: The expected shape of pixel values per image per batch...

https://github.com/XinzeZhang/HUST-PhD-Thesis-Latex/pull/33#issue-2881563132 hello, I have created a pr to support this feature. @wangshengseee @pikachubz @XinzeZhang

> > 改了cls和cover.tex之后编译会出错 请确保 cls 中所有改动均已修改。参见：https://github.com/XinzeZhang/HUST-PhD-Thesis-Latex/pull/33/files

已提交最新代码以解决在两张卡上部署的问题，关键修改是在子进程启动后再加载 torch 相关包

修改 cuda_devices https://github.com/VITA-MLLM/VITA/blob/6a26b5cbe1472e9854072d4add674108ae5c6504/web_demo/server.py#L992 https://github.com/VITA-MLLM/VITA/blob/6a26b5cbe1472e9854072d4add674108ae5c6504/web_demo/server.py#L1013

能否添加一个全局唤醒的快捷键，例如 chatgpt mac 端可以用 option+space 唤醒出对话框。