/plushcap/analysis/together-ai/together-ai-medusa

Medusa: Simple framework for accelerating LLM generation with multiple decoding heads

What's this blog post about?

Company
Together AI

Date published
Sept. 11, 2023

Author(s)
Tianle Cai*, Yuhong Li*, Zhengyang Geng, Hongwu Peng, Tri Dao (* Equal contribution)

Word count
2817

Language
English

Hacker News points
None found.


By Matt Makai. 2021-2024.