Reshape propagation to enable broadcast(transpose) -> attention(q, kt, vt) fusion. #19661
+53
−4
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…, 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 <[email protected]>
MaheshRavishankar
force-pushed
the
attention_v_transpose_fusion
branch
from
b9df00f to
568e472
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.