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

Compile GLU #1049

Merged
merged 1 commit into from
Mar 22, 2024
Merged

Compile GLU #1049

merged 1 commit into from
Mar 22, 2024

Conversation

josejg
Copy link
Contributor

@josejg josejg commented Mar 21, 2024

This PR adds torch.compile to the MPTGLU layer forward.

Under a LLaMa-2-7b-like workload (displayed below) adding torch.compile produces an additional ~100 tok/s/gpu with no changes in the loss

image

@josejg josejg merged commit 26a5fd4 into mosaicml:main Mar 22, 2024
10 checks passed
jjanezhang pushed a commit that referenced this pull request Mar 25, 2024
KuuCi pushed a commit that referenced this pull request Apr 18, 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

Successfully merging this pull request may close these issues.

None yet

2 participants