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

请问fastmoe能被集成到VLLM里吗 #191

Open
pangsg opened this issue Feb 4, 2024 · 4 comments
Open

请问fastmoe能被集成到VLLM里吗 #191

pangsg opened this issue Feb 4, 2024 · 4 comments

Comments

@pangsg
Copy link

pangsg commented Feb 4, 2024

No description provided.

@laekov
Copy link
Owner

laekov commented Feb 4, 2024

好问题. 目前没有这样的尝试.

@laekov
Copy link
Owner

laekov commented Feb 4, 2024

FastMoE 的单卡版本或多卡并行版本并不涉及对 kv-cache 进行变动. 理论上和 page attention 是正交关系. 可以一起用.

@pangsg
Copy link
Author

pangsg commented Feb 4, 2024 via email

@pangsg
Copy link
Author

pangsg commented Feb 8, 2024

定义MOE的时候,需要显式的self.moe().cuda()这样去把fastmoe layer放到GPU上吗

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

2 participants