GLIDE with a CAPE: A low-hassle method to accelerate speculative decoding

Author

• Cunxiao DU, Singapore Management UniversityFollow
• Jing JIANG, Singapore Management UniversityFollow
• Yuanchen XU
• Jiawei WU
• Sicheng YU
• Yongqi LI
• Shenggui LI
• Kai XU
• Liqiang NIE
• Zhaopeng TU
• Yang YOU

Publication Type

Conference Proceeding Article

Publication Date

7-2024

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems | Software Engineering

Research Areas

Data Science and Engineering

Publication

Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria, July 21-27

Volume

235

First Page

11704

Last Page

11720

Publisher

ML Research Press

City or Country

Vienna

Citation

DU, Cunxiao; JIANG, Jing; XU, Yuanchen; WU, Jiawei; YU, Sicheng; LI, Yongqi; LI, Shenggui; XU, Kai; NIE, Liqiang; TU, Zhaopeng; and YOU, Yang. GLIDE with a CAPE: A low-hassle method to accelerate speculative decoding. (2024). Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria, July 21-27. 235, 11704-11720.
Available at: https://ink.library.smu.edu.sg/sis_research/11109

Additional URL

https://proceedings.mlr.press/v235/du24c.html