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 FP8 on compute capability >=8.0, <8.9 #2213

Merged
merged 1 commit into from
Jul 11, 2024

Conversation

danieldk
Copy link
Member

What does this PR do?

Use FP8 GPTQ-Marlin kernels to enable FP8 support on CUDA GPUs with compute capability >=8.0 and <8.9.

Implemented together with @flozi00, who did the initial work in #2204.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@danieldk danieldk mentioned this pull request Jul 10, 2024
Use FP8 GPTQ-Marlin kernels to enable FP8 support on CUDA GPUs
with compute capability >=8.0 and <8.9.

Co-authored-by: Daniël de Kok <me@danieldk.eu>
@danieldk danieldk force-pushed the feature/fp8-marlin branch from 74fdd83 to dd0ed67 Compare July 10, 2024 12:09
Copy link
Member

@OlivierDehaene OlivierDehaene left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great! Thanks!

@danieldk danieldk merged commit cb150eb into main Jul 11, 2024
9 checks passed
@danieldk danieldk deleted the feature/fp8-marlin branch July 11, 2024 14:03
ErikKaum pushed a commit that referenced this pull request Jul 26, 2024
Use FP8 GPTQ-Marlin kernels to enable FP8 support on CUDA GPUs
with compute capability >=8.0 and <8.9.

Co-authored-by: Florian Zimmermeister <flozi00.fz@gmail.com>
yuanwu2017 pushed a commit to yuanwu2017/tgi-gaudi that referenced this pull request Sep 26, 2024
Use FP8 GPTQ-Marlin kernels to enable FP8 support on CUDA GPUs
with compute capability >=8.0 and <8.9.

Co-authored-by: Florian Zimmermeister <flozi00.fz@gmail.com>
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.

3 participants