FasterDecoding/Medusa

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

2.8k stars · 206 forks · Jupyter Notebook

At risk

At risk: no human commits in a year.

Why

What would change this

Maintenance

Complete

Dormant

Human commits, 30 days
0
Human commits, 90 days
0
Human commits, 365 days
0
Bot share of commits, 365 days
0%
Last commit
Apr 18, 2024 (2 years ago)
Last human commit
Apr 18, 2024 (2 years ago)
Authors, 90 days
0
Last release
Sep 11, 2023 (3 years ago)
Median PR merge time
under an hour

Responsiveness: of 2 recent issues, n/a got a maintainer reply. Median first response: n/a.

Sources: Commits, Releases, Merged pull requests, Issues

People

Complete
Owner
Organization
Commits sampled
72 since Sep 10, 2023
Authors for half of commits
2
Authors for 80% of commits
3
Contributors
10

Top committers

Sources: Commits, Contributors

Stars

Complete

Organic, confidence high

Stars per week, 2023-09-03 to 2026-10-11. 1 weeks overlap a burst.Peak 636 a week2023-09-032026-10-11
Bars show stars gained each week. Orange bars overlap a burst.

Bursts

Anyone can buy stars for any repo; bursts alone don't prove the owner did.

Sources: How star history is analyzed

Risk

Complete

Flags

No risk flags.

License

Now
Apache-2.0 (OSI-approved)
A year ago
Apache-2.0 (OSI-approved)

Packages

Package and advisory data: deps.dev and OSV.

Sources: GitHub: FasterDecoding/Medusa, deps.dev: PyPI medusa-llm

Badge

Add this to a README to show the current verdict:

[![RepoRadar](https://reporadar.ai/FasterDecoding/Medusa/badge.svg)](https://reporadar.ai/FasterDecoding/Medusa)

Earlier verdicts

Computed 3 hours ago · method 2026.10.2