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
- Can't run Mistral quantized on T4
- When caching adapters, cache the adapter ID + the API token pair
- `make install` insufficient for running llama3-8B-Instruct
- Some error records and questions
- Latency increase when run on multi-GPU
- ValueError: Adapter '/data/llama2-lora' is not compatible with model '/data/Llama-2-7b-chat-hf'. Use --model-id '/new-model/llama2-7b/Llama-2-7b-chat-hf' instead.
- Error deploying GPTQ models to sagemaker
- Issue using adapter with large prompt + sharded
- Want Lorax with newer version of TGI
- Second GPU is not found when running --sharded true
- Docs
- Python not yet supported