Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Accelerate the generation of large language models using a simple framework that supports multiple decoding methods.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeMedusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Medusa has 2.8k stars on GitHub. It has been forked 205 times. Medusa is written mainly in Jupyter Notebook. It has been in active development since 2023. Medusa is available under the Apache-2.0 license. Its main topics are llm, llm-inference.
What is Medusa?
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Is Medusa open source?
Medusa is an open-source project. It is released under the Apache-2.0 license.
Is Medusa free?
Yes. Medusa is free and open source — you can use, modify and self-host it.
What license does Medusa use?
Medusa is available under the Apache-2.0 license.
What language is Medusa written in?
Medusa is written mainly in Jupyter Notebook.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/fasterdecoding-medusa.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.