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
- Inference with AWQ quantized base model + compile enabled results in the <unk> tokens
- Combining multiple LoRA adapters
- Idefics2 and LLaVA
- Llama3-8b-Instruct won't stop generating
- Bug Report: lorax-launcher failed with --source "s3" for model_id "mistralai/Mistral-7B-Instruct-v0.2"
- Add HTTP status codes to docs
- Fuse allgather requests across adapters and q, k, v to reduce small network requests
- getting error during inference "Unsupported head size: 32"
- vision language model support
- Support self-trained model
- Docs
- Python not yet supported