Genghan Zhang (张庚瀚)

mypic.jpg
zgh23[at]stanford[dot]edu

I’m a second-year Ph.D. student in Stanford University Department of Computer Science advised by Professor Kunle Olukotun. I was also privileged to work with Professor Fredrik Kjolstad and Professor Azalia Mirhoseini.

I graduated from Tsinghua University in 2023 with a degree in Eletronic Engineering. At Tsinghua, I was fortunate enough to do research at NICS-EFC Lab and IDEAL Lab.

Research: My research interests lie in better programming models and systems for domain-specific architectures. I am also interested in optimizing GPU kernels for emerging applications, including sparse and recurrent neural networks.

Here is my CV. This site was last updated on September 27th, 2024.

News

Jul 9, 2024 Our paper “CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models” was accepted by COLM 2024!
Apr 1, 2024 Our paper “Compilation of Modular and General Sparse Workspaces” was accepted by PLDI 2024!
Nov 12, 2022 We built a frontend for Canvas to demonstrate Kernel Architecture Search. Just have a try! Available at Canvas.

Selected Publications

  1. PLDI
    Compilation of Modular and General Sparse Workspaces
    Genghan ZhangOlivia Hsu, and Fredrik Kjolstad
    Proceedings of the ACM on Programming Languages 2024
  2. CCFTHPC
    Sgap: towards efficient sparse tensor algebra compilation for GPU
    Genghan Zhang, Yuetong Zhao, Yanting Tao, Zhongming YuGuohao DaiSitao HuangYuan WenPavlos Petoumenos, and Yu Wang
    CCF Transactions on High Performance Computing 2023

Service

  • Reviewer: ICLR 2025, NeurIPS 2024
  • Workshop Reviwer: NeurIPS 2024 Sys2-Reasoning, NeurIPS 2022 GLFrontiers