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

Reshape propagation to enable broadcast(transpose) -> attention(q, kt, vt) fusion. #19661

Conversation

MaheshRavishankar
Copy link
Contributor

Fixes some minor bugs and adds a missing pattern to enable reshape propagation that moves reshapes out of the transpose operation and attention operation to be fusable subsequently.

This doesnt necessarily fuse the the transpose and attention yet. That will be addressed subsequently.

…, vt) fusion.

Fixes some minor bugs and adds a missing pattern to enable reshape
propagation that moves reshapes out of the transpose operation and
attention operation to be fusable subsequently.

Signed-off-by: MaheshRavishankar <mravisha@amd.com>
@MaheshRavishankar MaheshRavishankar force-pushed the attention_v_transpose_fusion branch from 568e472 to 99c47b5 Compare January 13, 2025 00:44
@MaheshRavishankar
Copy link
Contributor Author

@MaheshRavishankar MaheshRavishankar merged commit d90c505 into iree-org:main Jan 13, 2025
36 checks passed
@MaheshRavishankar MaheshRavishankar deleted the attention_v_transpose_fusion branch January 13, 2025 17:03
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.

2 participants