Yilong Zhao (赵一龙)

I’m a Ph.D. student in Sky Computing Lab at UC Berkeley, advised by Prof. Ion Stoica. I received my B.Eng. in Computer Science from ACM Honor Class at Shanghai Jiao Tong University. During my senior year, I was fortunate to work with Prof. Baris Kasikci at University of Washington.

My research interests lie in building effient system support for AI applications, drawing insights from both system and algorithm sides.

Publications


* means equal contribution

  1. ../nanoflow2.png
    NanoFlow: Towards Optimal Large Language Model Serving Throughput
    Kan Zhu, Yilong Zhao, Liangyu Zhao, Gefei Zuo, Yile Gu, Dedong Xie, Yufei Gao, Qinyu Xu, Tian Tang, Zihao Ye, Keisuke Kamahori, Chien-Yu Lin, Stephanie Wang, Arvind Krishnamurthy, Baris Kasikci
  2. ../quest.png
    Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
    Jiaming Tang*Yilong Zhao*, Kan Zhu, Guangxuan Xiao, Baris Kasikci, Song Han
  3. ../atom2.png
    Atom: Low-Bit Quantization for Efficient and Accurate LLM Serving
    Yilong Zhao, Chien-Yu Lin, Kan Zhu, Zihao Ye, Lequn Chen, Size Zheng, Luis Ceze, Arvind Krishnamurthy, Tianqi Chen, Baris Kasikci