text-generation-inference
https://github.com/huggingface/text-generation-inference
Python
Large Language Model Text Generation Inference
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 text-generation-inference
Help out
- Issues
- The TGI loading model consumes all available gpus memory
- Support for ReFT
- Python client: Extra slash in base_uri leads to failures in chat endpoint
- Planned/Potential of significant work
- Changing the waiting_served_ratio default (stack more aggressively by default).
- Suport for InternVL-Chat-V1-5
- Frequency penalty corrupting generations
- Fixing frequency penalty
- feat: add one line quickstart
- feat: add vlm docs and simple examples
- Docs
- Python not yet supported