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

Question: How do I use openblas on M1 apple silicon (or is there any point?) #857

Closed
dogjamboree opened this issue Apr 8, 2023 · 2 comments

Comments

@dogjamboree
Copy link

I don't quite how to specify the proper make flag for this or whether it even applies to MacOS.

@cmp-nct
Copy link
Contributor

cmp-nct commented Apr 9, 2023

OpenBLAS has barely any benefit, it's speeding up prompt ingestion but not token generation.
On M1 you have the accelerate framework built in, I'm quite sure that will be superior

@dogjamboree
Copy link
Author

OpenBLAS has barely any benefit, it's speeding up prompt ingestion but not token generation. On M1 you have the accelerate framework built in, I'm quite sure that will be superior

THanks, I'll close this then.

jeroen-mostert pushed a commit to jeroen-mostert/llama.cpp that referenced this issue Aug 30, 2024
* Harden against conda hijacks

Turns out conda can override the location of our packages, by ignoring the conda rc files we can prevent this.

* Harden even further

Turns out not everything has a --no-rc option, now we hardcode the path.

* Remove --no-rc in run

Not supported in run, breaks the commands.
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

No branches or pull requests

2 participants