FasterDecoding

FasterDecoding

Organization data from Github https://github.com/FasterDecoding

Think deeper, decode faster

Location:United States of America

GitHub:@FasterDecoding

FasterDecoding's repositories

Medusa

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

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:2659Issues:28Issues:98
Language:PythonLicense:Apache-2.0Stargazers:287Issues:6Issues:27

REST

REST: Retrieval-Based Speculative Decoding, NAACL 2024

Language:CLicense:Apache-2.0Stargazers:210Issues:7Issues:25
Language:Jupyter NotebookLicense:Apache-2.0Stargazers:202Issues:5Issues:5
Language:PythonLicense:MITStargazers:142Issues:3Issues:12