feat: add ruy sgemm implementation#1598
Merged
minhthuc2502 merged 2 commits intoOpenNMT:masterfrom Mar 25, 2024
Merged
Conversation
Contributor
Author
|
This and #1600 are relatively small PRs with no side effects, can you review them? @minhthuc2502 maybe you can take a look :) |
Collaborator
|
Hello @ebraraktas, sorry for the late response. |
Contributor
Author
|
@minhthuc2502 I moved the implementation as requested. |
Collaborator
|
Thanks. I relaunched the failed CI. I'll merge then |
ebraraktas
force-pushed
the
feat/ruy-sgemm-backend
branch
from
93216b9 to
302ca69
Compare
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 adds SGEMM implementation with RUY. This is already mentioned in
faster-whisperrepository.I implemented this, because my experience with BLAS on Android was worse than this, and BLAS performance was not consistent (It sometimes takes too long). In addition, this requires no additional dependency and allows one to use
ctranslate2without BLAS.