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

optimize dependences #2147

Merged
merged 2 commits into from
Aug 8, 2023
Merged

optimize dependences #2147

merged 2 commits into from
Aug 8, 2023

Conversation

liunux4odoo
Copy link
Contributor

@liunux4odoo liunux4odoo commented Aug 3, 2023

Why are these changes needed?

as suggested by #2045, #2129, it would be better to make some dependences optional for different service scenarios.

this pr suppose fastchat will be used in 3 different ways:

  1. a controller and openai api server, no torch is required.
  2. a model_woker as a LLM api server, torch is required.
  3. the user need a web interface built by gradio in addition to the api server.

both of torch and gradio require a large installation capacity. It is efficient for distributed installations to make them optional.

Related issue number (if applicable)

#2045, #2129

Checks

  • I've run format.sh to lint the changes in this PR.
  • I've included any doc changes needed.
  • I've made sure the relevant tests are passing (if applicable).

@merrymercy merrymercy merged commit b13b2dc into lm-sys:main Aug 8, 2023
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants