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

[BugFix] skip loading lm_head for llama if word embeddings are tied #6796

Closed

Conversation

prashantgupta24
Copy link
Contributor

@prashantgupta24 prashantgupta24 commented Jul 25, 2024

Check if tie_word_embeddings is true, that means lm_head is tied to embeddings we should be able to skip loading lm_head

Similar to what was done for gemma here - #3553

Since lm_head is tied to embeddings we should be able to skip loading lm_head

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Copy link

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which consists a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of default ones by unblocking the steps in your fast-check build on Buildkite UI.

Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge).

To run full CI, you can do one of these:

  • Comment /ready on the PR
  • Add ready label to the PR
  • Enable auto-merge.

🚀

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
@prashantgupta24 prashantgupta24 changed the title 🐛 skip loading lm_head [BugFix] skip loading lm_head for llama if word embeddings are tied Jul 25, 2024
@DarkLight1337 DarkLight1337 requested a review from simon-mo July 26, 2024 11:59
@DarkLight1337
Copy link
Member

Seems that it has already been done in #6758. Would you mind if the other PR is adopted instead?

@prashantgupta24
Copy link
Contributor Author

Closing in favor of #6758

@prashantgupta24 prashantgupta24 deleted the lm-head-llama branch August 20, 2024 18:43
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