Skip to content

ggml : Add GGML_USE_SVE macro to disable SVE by default #8426

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

Closed

Conversation

msy-kato
Copy link
Contributor


This PR addresses an issue introduced in #8109.

In the previous update, GGML_NATIVE was enabled by default, which in turn enabled SVE by default. However, SVE currently only supports 256-bit operations in vec_dot, leading to errors when running on SVE 128-bit CPUs.

This fix ensures that SVE is not enabled unless GGML_SVE=ON is explicitly set at compile time.

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Jul 11, 2024
@slaren
Copy link
Member

slaren commented Jul 11, 2024

If I am not mistaken, this has already been addressed in #5780 by making it fall back to the NEON implementation if the vector size is not 256-bit.

@msy-kato
Copy link
Contributor Author

msy-kato commented Jul 11, 2024

Thank you for comment, I missed that correction. It looks good. I close this PR.

@msy-kato msy-kato closed this Jul 11, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ggml changes relating to the ggml tensor library for machine learning
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants