I am a 4th-year CS undergraduate student at Beihang University. In 2024 fall, I will also participate in the exchange student program at the University of Macau.
Currently I am a research assistant advised by Prof. Huanle Xu on LLM inference system optimization and efficient scheduling. Before that, I was advised by Prof. Zhongzhi Luan on performance optimization and parallel computing.
My current research interests are broadly in the intersection between systems and machine learning, performance optimization and efficient scheduling of LLM systems for instance. At the same time, I am now very fascinated by the challenge of how to handle the deployment of new LLM optimization techniques into the system, for example work like SpecInfer.
For more details of personal projects, interests and knowledge, please refer to the CV and my blogs website.
I am looking for Research Assistant position starting from Spring 2025 or Ph.D. position starting from Fall 2025. I would greatly appreciate any opportunity for further discussion.
CONTACT
RECENT NEWS
[2024.06] I will be working as a RA and exchange student at the University of Macau until Dec. 2024.
[2023.12] One paper is accepted by HPCC2023.