Content Deep Dive
Medusa: Simple framework for accelerating LLM generation with multiple decoding heads
Company
Together AI
Date Published
Sept. 11, 2023
Author
Tianle Cai*, Yuhong Li*, Zhengyang Geng, Hongwu Peng, Tri Dao (* Equal contribution)
Word count
2817
Language
English
Hacker News points
None
URL
www.together.ai/blog/medusa
Summary
No summary generated yet.