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

Unpatch llama #572

Closed
wants to merge 17 commits into from
Closed

Conversation

jiqing-feng
Copy link
Collaborator

@jiqing-feng jiqing-feng commented Feb 27, 2024

Hi @echarlaix . This PR is derived from #567 , I integrate the llama model patcher with patch and un-patch.

It has 2 main differences in performance compared with #567 :

  1. The memory is increased by 90%
  2. The latency is increased by 8%

If you think the extra memory and latency regression are acceptable, we can review this PR instead. Thx!

@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.

@jiqing-feng jiqing-feng mentioned this pull request Mar 7, 2024
@echarlaix echarlaix closed this Mar 8, 2024
@jiqing-feng jiqing-feng deleted the unpatch_llama branch March 11, 2024 07:00
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