OTAS: An Elastic Transformer Serving System via Token Adaptation

Jinyu Chen, Wenchao Xu, Zicong Hong, Song Guo, Haozhao Wang, Jie Zhang, Deze Zeng
May 2024
PDF
Type
Conference paper
Publication
IEEE International Conference on Computer Communications (INFOCOM) (CCF-A)
Jinyu Chen
Jinyu Chen
PhD, 2022-Now
Wenchao Xu
Wenchao Xu
Research Assistant Professor
Zicong Hong
Zicong Hong
PhD, 2020-2024, HKPFS
Song Guo
Song Guo
Chair Professor
Jie Zhang
Jie Zhang
Research Assistant Professor
Deze Zeng
Deze Zeng
PhD, 2009-2013, Associate Dean and Professor in SCS at China University of Geosciences, The National Youth Talent Support Program