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

ROCm: make CK FA2 default instead of Triton #1924

Merged
merged 2 commits into from
May 20, 2024
Merged

ROCm: make CK FA2 default instead of Triton #1924

merged 2 commits into from
May 20, 2024

Conversation

fxmarty
Copy link
Contributor

@fxmarty fxmarty commented May 20, 2024

As per title.

Triton autotune overhead is prohibitive, as it needs to be done for each different prompt length.

@fxmarty
Copy link
Contributor Author

fxmarty commented May 20, 2024

(will merge directly for tomorrow)

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@fxmarty fxmarty merged commit 293b812 into main May 20, 2024
3 of 4 checks passed
@fxmarty fxmarty deleted the rocm-ck-default branch May 20, 2024 00:44
yuanwu2017 pushed a commit to yuanwu2017/tgi-gaudi that referenced this pull request Jul 17, 2024
As per title.

Triton autotune overhead is prohibitive, as it needs to be done for each
different prompt length.
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