lorax
https://github.com/predibase/lorax
Python
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to lorax
Help out
- Issues
- feat: reject unknown fields from API requests (fixes #478)
- Reject unknown fields from native API request bodies
- docs: add HTTP status codes reference page (fixes #481)
- Set object to "chat.completion" for non-streaming chat completions
- Add HTTP status codes to docs
- feat(router): support OpenAI-compatible max_completion_tokens alias
- Bump torch from 2.4.0 to 2.6.0 in /server
- fix cve
- Request for Clarification on LoRA Adapter Portability, Merging, and Benchmarks
- Title: stream=True only returns output from basemodel, LoRA adapter is ignored.
- Docs
- Python not yet supported