[Docs] 多模态模型的api_server应该如何多卡部署？
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
### 📚 The doc issue
如题，多卡部署的话直接在启动命令里面指定`--tp`就行了吗？另外文档里推荐的多模态模型`liuhaotian/llava-v1.6-vicuna-7b`部署时的推荐最低显卡配置是什么，大概能够实现多少的并发请求量。感谢回复。
### Suggest a potential alternative/fix
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.