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

iqk_mul_mat(ARM_NEON): adding bf16 support #41

Merged
merged 1 commit into from
Sep 16, 2024
Merged

iqk_mul_mat(ARM_NEON): adding bf16 support #41

merged 1 commit into from
Sep 16, 2024

Conversation

ikawrakow
Copy link
Owner

It looks like ArmV8 ISA has support for bf16, but my M2 Max does not have it, so resorting to bf16 -> f32 conversion and computations in f32. This is 2X slower than f16, but 8X better compared to what I get if I try to run a bf16 model on the M2 (NEON and Metal).

It looks like ArmV8 ISA has support for bf16, but my M2 Max
does not have it, so resorting to bf16 -> f32 conversion and
computations in f32. This is 2x slower than f16, but 8x better
compared to what I get if I try to run a bf16 model on the M2
(NEON and Metal).
@ikawrakow ikawrakow merged commit 2874b98 into main Sep 16, 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