FasterDecoding/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Jupyter NotebookApache-2.0
Stargazers
- abacajsoftware eng building things
- abodacsOpenCoast
- akansal1
- BQZicPrinceton University
- ctlllll@Princeton
- danielz02Massachusetts Institute of Technology
- GsunshineCMU
- guanchuwangRice University
- harveyp123University of Connecticut
- kaidicStanford University
- KyriectionThe University of Texas at Austin
- leeyeehooBurger Shot
- lsj2408Peking University @microsoft
- marclove@carbonfive
- Matthieu-Tinycoaching
- MemorySlicesPrinceton University
- merrymercyUC Berkeley
- MuhtashamTU Munich
- pgarbackiPinterest
- rajaswa-postman@postman-eng @postmanlabs
- s1ghhh
- saivigNew Delhi, India
- SakinaWEIChatGLM
- Spico197Soochow University
- TheSeamau5Entrepreneur
- tiangeluo
- TobyGEUSA
- tristanz@continual-ai
- varshith15
- vgoklaniNew York, NY
- vtu81Princeton University
- WhenWenShenzhen
- xiyuzhaiMIT
- yzhangcsSoochow University
- zguo0525
- zyxieTwitter