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.

Sign up for GitHub

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

Jump to bottom

TF32 support, MI300 & MI325 spec list TF32 performance numbers but it seems there is no way of enabling it in pytorch #1911

Open
Delaunay opened this issue Feb 18, 2025 · 2 comments
Open

TF32 support, MI300 & MI325 spec list TF32 performance numbers but it seems there is no way of enabling it in pytorch #1911

Delaunay opened this issue Feb 18, 2025 · 2 comments
Labels
Under Investigation

Comments

@Delaunay
Copy link

Delaunay commented Feb 18, 2025 •
edited
Loading

🚀 The feature, motivation and pitch

TF32 support, MI300 & MI325 spec list TF32 performance numbers, but it seems there is no way of enabling it in pytorch
as per the torch compat document.

TF32 yields significant performance uplift across the board.

Alternatives

No response

Additional context

No response
@ppanchad-amd
Copy link

Hi @Delaunay. Internal ticket has been created to assist with your issue. Thanks!

@adityas-amd
Copy link

@Delaunay there is a tf32 support for earlier versions of ROCm/Pytorch in the [release/2.5] branch #1838

@Delaunay Delaunay mentioned this issue Mar 6, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Under Investigation
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@Delaunay @ppanchad-amd @adityas-amd