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
- Just wanna know
- feat: LoRAX On-Premise Deployment Playbook & DX Enhancements
- Lorax Stop Responding after non-concurrent/concurrent requests
- Question regarding BERT
- Add handler logic to ner
- Kernel issues, with docker image:main
- Potential race condition
- Deprecate max_tokens in favor of max_completion_tokens
- Support for DeepSeek-based models
- Beam search support
- Docs
- Python not yet supported