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.

Sign up for GitHub

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

Jump to bottom

Allow N-D inputs to triton fp8 row quantize #3225

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Allow N-D inputs to triton fp8 row quantize #3225

wants to merge 1 commit into from

Commits on Oct 4, 2024

  1. Allow N-D inputs to triton fp8 row quantize 

    Summary: We previously assumed inputs to fp8 quantize would be 2D, however we now are working with higher dimension workloads that would benefit from FP8. This small diff adds more general shape checking to fp8 quantization.

Differential Revision: D63921964
    @jwfromm @facebook-github-bot
    jwfromm authored and facebook-github-bot committed Oct 4, 2024
    Configuration menu
    Copy the full SHA
    a5ff8da View commit details
    Browse the repository at this point in the history