TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding.
Zhaoxuan Wu, Zijian Zhou, Arun Verma, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low
Browse the full ACL paper archive.
Zhaoxuan Wu, Zijian Zhou, Arun Verma, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low
Browse the full ACL paper archive.