Skip to content

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