Yifei Liu

Researcher at RAI Studio, Xiaohongshu

liuyifei.jpeg

Hi, I am an LLM infrastructure researcher at RAI Studio, Xiaohongshu. I received my M.S. degree from Shanghai Jiao Tong University, where I was a member of the Emerging Parallel Computing Center (EPCC) and was advised by Professor Chen Chen. Previously, I worked on LLM inference optimization with the XDS Team at Huawei Cloud, where I was fortunate to work with and be mentored by Yizhou Shan.

My research focuses on building efficient LLM inference systems. I have also worked on cluster scheduling and distributed caching.

For more information, please explore this website or refer to my CV.

Selected Publications

  1. ATC (CCF-A)
    HAPIC: Position-Independent Caching for Hybrid-Attention LLM Serving
    Yifei Liu, Juntong Wu, Yang Liu, Junhao Hu, Minghao Li, Xiaoxu Chen, and Weihang Chen
    ACM SIGOPS Annual Technical Conference, 2026
    Paper Code
  2. TACO (CCF-A)
    Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling
    Yifei Liu, Zuo Gan, Zhenghao Gan, Weiye Wang, Chen Chen, Yizhou Shan, Xusheng Chen, Zhenhua Han, Yifei Zhu, Shixuan Sun, and Minyi Guo
    ACM Transactions on Architecture and Code Optimization, 2026
    Paper Code
  3. TACO (CCF-A)
    Ares: Fair and Efficient Scheduling of Deep Learning Jobs with Elastic Fair Queuing
    Yifei Liu, Chen Chen, Qiang Wang, Yu Feng, Weihao Cui, Quan Chen, and Minyi Guo
    ACM Transactions on Architecture and Code Optimization, 2025
    Paper Code