Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

支持跨主机部署模型推理 #1472

Open
lordk911 opened this issue May 10, 2024 · 5 comments
Open

支持跨主机部署模型推理 #1472

lordk911 opened this issue May 10, 2024 · 5 comments
Milestone

Comments

@lordk911
Copy link

vLLM官方文档称可利用ray实现模型多机推理

xinference launch model 时只能选择本机的显卡,希望可以支持跨主机部署模型推理

@XprobeBot XprobeBot added this to the v0.11.0 milestone May 10, 2024
@qinxuye
Copy link
Contributor

qinxuye commented May 10, 2024

这么做在 xinf 中实现并不难,但我比较质疑多机 TP 的效率。

@lordk911
Copy link
Author

这么做在 xinf 中实现并不难,但我比较质疑多机 TP 的效率。

嗯,好处是可以低成本去验证大尺寸模型,来为硬件投入做参考;对产品自身来讲也是个比较好的宣传点。

@XprobeBot XprobeBot modified the milestones: v0.11.0, v0.11.1 May 11, 2024
@zhanghaiqiangshigezhu
Copy link

目前xinference支持一个模型部署在多台机器上么?

@zhanghaiqiangshigezhu
Copy link

这么做在 xinf 中实现并不难,但我比较质疑多机 TP 的效率。

目前xinference支持一个模型部署在多台机器上么?

@zhanghaiqiangshigezhu
Copy link

这么做在 xinf 中实现并不难,但我比较质疑多机 TP 的效率。

嗯,好处是可以低成本去验证大尺寸模型,来为硬件投入做参考;对产品自身来讲也是个比较好的宣传点。

目前xinference支持一个模型部署在多台机器上么?

@XprobeBot XprobeBot modified the milestones: v0.11.1, v0.11.2 May 17, 2024
@XprobeBot XprobeBot modified the milestones: v0.11.2, v0.11.3 May 24, 2024
@XprobeBot XprobeBot modified the milestones: v0.11.3, v0.11.4 May 31, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants