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

feat: add ruy sgemm implementation #1598

Merged
merged 2 commits into from
Mar 25, 2024

Conversation

ebraraktas
Copy link
Contributor

This PR adds SGEMM implementation with RUY. This is already mentioned in faster-whisper repository.

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 ctranslate2 without BLAS.

@ebraraktas
Copy link
Contributor Author

This and #1600 are relatively small PRs with no side effects, can you review them? @minhthuc2502 maybe you can take a look :)

@minhthuc2502
Copy link
Collaborator

minhthuc2502 commented Mar 5, 2024

Hello @ebraraktas, sorry for the late response.
I think you should add implementation of RUY after BLAS. The RUY implementation will be used if only the BLAS does not exist.

@ebraraktas
Copy link
Contributor Author

@minhthuc2502 I moved the implementation as requested.

@minhthuc2502
Copy link
Collaborator

Thanks. I relaunched the failed CI. I'll merge then

@minhthuc2502 minhthuc2502 merged commit b7415b2 into OpenNMT:master Mar 25, 2024
17 checks passed
@ebraraktas ebraraktas deleted the feat/ruy-sgemm-backend branch March 25, 2024 12:25
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