Better CPU prompt processing performance for SWA models#702
Closed
Better CPU prompt processing performance for SWA models#702
Conversation
added 4 commits
August 18, 2025 07:58
This was referenced Sep 2, 2025
Merged
Owner
Author
|
Closing in favor of #757 |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR is a fixed version of #696, see there for details.
The crashes we were getting on #696 are due to the back-end not allocating a buffer for the tensor containing the mask bounds when this tensor is not used in the graph. Now we only create the mask bounds if they are actually used (SWA models with FA enabled).