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

Add support for bf16 to iqk_mul_mat #39

Merged
merged 3 commits into from
Sep 5, 2024
Merged

Add support for bf16 to iqk_mul_mat #39

merged 3 commits into from
Sep 5, 2024

Conversation

ikawrakow
Copy link
Owner

Only when natively supported (e.g., Zen4), else left to ggml to handle.

For LLaMA-3.1-8B we get PP512 = 205 t/s vs 74 t/s in llama.cpp on my Ryzen-7950X CPU.

I get 204 t/s with llamafile, so I guess Justine Tunney has not contributed the more recent tinyBLAS improvements to llama.cpp.

@ikawrakow ikawrakow changed the title Add support fr bf16 o iqk_mul_mat Add support fr bf16 to iqk_mul_mat Sep 4, 2024
@ikawrakow ikawrakow changed the title Add support fr bf16 to iqk_mul_mat Add support for bf16 to iqk_mul_mat Sep 4, 2024
@ikawrakow ikawrakow merged commit 0087008 into main Sep 5, 2024
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