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

How many H20 (96GB) GPUs are needed to train Qwen7B with the GRPO algorithm? #401

Open
Tuziking opened this issue Feb 27, 2025 · 2 comments

Comments

@Tuziking
Copy link

I want to use the GRPO algorithm to train Qwen7B, but I failed using 4 H20 (96GB) GPUs with the trl library. I hope to train it with the verl library and would like to know how many H20 GPUs are needed.

@vermouth1992
Copy link
Collaborator

I think 4 should be enough.

@Tuziking
Copy link
Author

I think 4 should be enough.我认为 4 个应该足够了。

Thank you, I will try!

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