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

Deprecate OpenAI backend once we've tested that LiteLLM can reach 500 RPS #336

Closed
vutrung96 opened this issue Jan 10, 2025 · 2 comments
Closed

Comments

@vutrung96
Copy link
Contributor

We have a separate implementation for OpenAI because LiteLLM could not go above 50 RPS, but they seem to have fixed the issue BerriAI/litellm#6592.

We should test this out, if we can reach 500 RPS with LiteLLM then we can deprecate OpenAI backend

@vutrung96
Copy link
Contributor Author

On the other hand, LiteLLM also has some performance issues, so maybe we shouldn't do this.....

@vutrung96
Copy link
Contributor Author

Ok, consensus seems to be that we should keep relying on our own OpenAI backend code...

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

No branches or pull requests

1 participant