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

ENH: <support datatype FP8> #26405

Closed
xiguadong opened this issue May 9, 2024 · 2 comments
Closed

ENH: <support datatype FP8> #26405

xiguadong opened this issue May 9, 2024 · 2 comments
Labels
33 - Question Question about NumPy usage or development

Comments

@xiguadong
Copy link

Proposed new feature or change:

Hi :
Do you have any plan to support FP8 which proposed in https://arxiv.org/pdf/2209.05433 ?

@jakevdp
Copy link
Contributor

jakevdp commented May 9, 2024

I don't know of any proposal to include fp8 types in numpy itself, but you might take a look at the ml_dtypes package, which defines several flavors of fp8 dtypes for use with NumPy.

@rgommers
Copy link
Member

+1 for ml_dtypes here.

We may end up incorporating bfloat16 into numpy itself at some point, but float8 seems like a bridge too far, at least in the near future (and no one has proposed actually doing this anyway). So I'll close this since the question is answered and a solution available. Thanks @xiguadong and @jakevdp

@rgommers rgommers added the 33 - Question Question about NumPy usage or development label May 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
33 - Question Question about NumPy usage or development
Projects
None yet
Development

No branches or pull requests

3 participants