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

Saving some VRAM. #2790

Merged
merged 2 commits into from
Dec 3, 2024
Merged

Saving some VRAM. #2790

merged 2 commits into from
Dec 3, 2024

Conversation

Narsil
Copy link
Collaborator

@Narsil Narsil commented Nov 30, 2024

  • 8B on 4xL4 attention=flashdecoding . Before 4.28GB left, After 4.32GB left, so 400MB saved.

  • Effect not as visible on attention=flashinfer and n_shard=1. I suspect it's linked to the torch allocator.

What does this PR do?

Fixes # (issue)

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.

- 8B on 4xL4 attention=flashdecoding . Before 4.28GB left, After 4.32GB
  left, so 400MB saved.

- Effect not as visible on attention=flashinfer and n_shard=1. I suspect
  it's linked to the torch allocator.
max_current_length=max_s,
)
else:
input_ids = self.cuda_graphs[max_bs]["input_ids"][:bs]
Copy link
Member

Choose a reason for hiding this comment

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

maybe add an assert here that max_bs > bs otherwise LGTM

@Narsil Narsil merged commit b57f370 into main Dec 3, 2024
8 of 12 checks passed
@Narsil Narsil deleted the fuse_graphs branch December 3, 2024 03:04
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