# fasterdecoding/medusa

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/fasterdecoding-medusa).**

2,751 stars · 201 forks · Jupyter Notebook · Apache-2.0

## Links

- GitHub: https://github.com/FasterDecoding/Medusa
- Homepage: https://sites.google.com/view/medusa-llm
- awesome-repositories: https://awesome-repositories.com/repository/fasterdecoding-medusa.md

## Description

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

## Tags

### Part of an Awesome List

- [Speculative Decoding](https://awesome-repositories.com/f/awesome-lists/ai/speculative-decoding.md) — Uses multiple decoding heads to speed up generation.