Jingzhi Fang
Email: jfangak [at] connect [dot] ust [dot] hk

This is Jingzhi Fang, a post-doctoral fellow in Prof. Xiaofang Zhou’s group in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST). I obtained my doctorate in Computer Science and Engineering (CSE) from HKUST under the supervision of Prof. Lei Chen. Before that, I received my bachelor’s degree from SHENYUAN Honors College at Beihang University (BUAA).
I am interested in accelerating the inference efficiency of deep learning models through computation graph and operator optimization, resource allocation, etc. My current work focuses on improving the efficiency of large language models (LLMs).
Earlier Projects
- STile: Searching Hybrid Sparse Formats for Sparse Deep Learning Operators Automatically, built upon SparseTIR, Apache TVM.
news
Aug 27, 2024 | We give a tutorial “Efficient Training of Graph Neural Networks on Large Graphs” at VLDB 2024 (tutorial github page). |
---|---|
May 25, 2024 | I build this page. ![]() |