STACKQUADRANT

FasterDecoding/Medusa

Inference Engines

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

GitHub Metrics
Stars
2.7k
Forks
194
Open Issues
57
Watchers
29
Contributors
11
Weekly Commits
0
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: Mar 3, 2026
Quality Scores
Documentation Qualityw: 20%
0.0
Community Healthw: 20%
0.0
Maintenance Velocityw: 15%
0.0
API Design & DXw: 20%
0.0
Production Readinessw: 15%
0.0
Ecosystem Integrationw: 10%
0.0
Tags
llmllm-inference
Radar
No scores yet