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

Fix slowdown on init with device_map="auto" #2914

Merged
merged 1 commit into from
Jul 4, 2024
Merged

Fix slowdown on init with device_map="auto" #2914

merged 1 commit into from
Jul 4, 2024

Conversation

muellerzr
Copy link
Collaborator

What does this PR do?

#2857 introduced using gc.collect() as part of the clear_device_cache. This is very slow to do and increases the time to load models exponentially when using device_map="auto" (e.g. llama-3-8B went from 6.663s to 37.535s).

This PR adds a garbage_collection flag which is False by default.

Fixes #2911

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.

@SunMarc

@muellerzr muellerzr requested a review from SunMarc July 4, 2024 13:03
Copy link
Member

@SunMarc SunMarc left a comment

Choose a reason for hiding this comment

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

LGTM!

@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.

@muellerzr muellerzr merged commit 2471eac into main Jul 4, 2024
28 checks passed
@muellerzr muellerzr deleted the fix-bug branch July 4, 2024 13:10
muellerzr added a commit that referenced this pull request Jul 4, 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.

Model loading extremely slow after upgrading from 0.31.0 to 0.32.0
3 participants