FasterDecoding/Medusa

Inference Engines

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

GitHub →Website →

5.5

GitHub Metrics

Stars

2.8k

Forks

206

Open Issues

Watchers

Contributors

Weekly Commits

Language

Jupyter Notebook

License

Apache-2.0

Last Commit

Jun 25, 2024

Created

Sep 10, 2023

Latest Release

v0.1

Release Date

Sep 11, 2023

Synced: Oct 18, 2026

Quality Scores

Documentation Qualityw: 20%

6.7

Has docs site (https://sites.google.com/view/medusa-llm). Description: 85 chars. Stars signal: 2,775. Contributors: 11. Score: 6.7/10

Community Healthw: 20%

5.7

Stars: 2,775. Contributors: 11. Watchers: 29. Forks: 206. Issue ratio: 2.1%. Score: 5.7/10

Maintenance Velocityw: 15%

0.8

Last commit: 844d ago. Weekly commits: 0. Latest release: v0.1. Maturity bonus: 3.1y old. Score: 0.8/10

API Design & DXw: 20%

7.2

Stars/issues ratio: 49. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 2,775 stars. Score: 7.2/10

Production Readinessw: 15%

5.0

Battle-tested: 2,775 stars. Peer review: 11 contributors. Versioned: v0.1. Licensed: Apache-2.0. Age: 3.1 years. Maintenance: last commit 844d ago. Score: 5/10

Ecosystem Integrationw: 10%

6.9

Fork interest: 206. Ecosystem: Jupyter Notebook. Integration-friendly: Apache-2.0. Adoption: 2,775 stars. Has web presence. Score: 6.9/10