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

Support PP inference for chatglm3 #11375

Merged
merged 3 commits into from
Jun 21, 2024

Conversation

plusbang
Copy link
Contributor

@plusbang plusbang commented Jun 20, 2024

Description

Support chatglm3 and update related PP example

2. User API changes

N/A

3. Summary of the change

  • Add split operations for chatglm model structure
  • Add num_layers config and other compatible processing
  • Add related example script

4. How to test?

  • Unit test
  • Local test
    image

Copy link
Contributor

@sgwhat sgwhat left a comment

Choose a reason for hiding this comment

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

Maybe we can use try/except instead of creating a new glm_generate.py.

@plusbang
Copy link
Contributor Author

Maybe we can use try/except instead of creating a new glm_generate.py.

Have updated.

@plusbang plusbang requested a review from sgwhat June 20, 2024 08:12
Copy link
Contributor

@sgwhat sgwhat left a comment

Choose a reason for hiding this comment

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

LGTM

@plusbang plusbang merged commit 4ba8219 into intel-analytics:main Jun 21, 2024
31 checks passed
RyuKosei pushed a commit to RyuKosei/ipex-llm that referenced this pull request Jul 19, 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.

2 participants