FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

Jiaao He, Jidong Zhai
January, 2024
Cite DOI URL
Type
Journal article
Publication
CoRR
Jiaao He
Jiaao He
Ph.D. Student
Jidong Zhai
Jidong Zhai
Professor
(长聘教授、博士生导师)