Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Loading...
Links
- Source: https://github.com/FasterDecoding/Medusa
- JSON API: repos.ecosyste.ms
-
PURL:
pkg:github/FasterDecoding/Medusa
Repository Details
- Stars 2,708
- Forks 193
- Open issues 57
- License apache-2.0
- Language Jupyter Notebook
- Size 4.76 MB
- Created at over 2 years ago
- Updated at 3 days ago
- Pushed at over 1 year ago
- Last synced at about 1 hour ago
- Dependencies parsed at Pending
Topics