FasterDecoding / Medusa

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

Date Created 2023-09-10 (about a year ago)

Commits 72 (last one 8 months ago)

Stargazers 2,348 (10 this week)

Watchers 31 (0 this week)

Forks 163

License apache-2.0

Ranking

RepositoryStats indexes 595,856 repositories, of these FasterDecoding/Medusa is ranked #21,966 (96th percentile) for total stargazers, and #70,804 for total watchers. Github reports the primary language for this repository as Jupyter Notebook, for repositories using this language it is ranked #507/17,543.

FasterDecoding/Medusa is also tagged with popular topics, for these it's ranked: llm (#265/2913), llm-inference (#17/171)

Other Information

FasterDecoding/Medusa has 4 open pull requests on Github, 20 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 46 open issues and 46 closed issues.

There have been 1 release, the latest one was published on 2023-09-11 (about a year ago) with the name Medusa-v0.1.

Homepage URL: https://sites.google.com/view/medusa-llm

All Topics

llm llm-inference

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

72 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Jupyter Notebook but there's also others...

updated: 2024-12-22 @ 02:46am, id: 689541424 / R_kgDOKRmRMA