Zhenyuan Yang Operating Systems & ML Systems

Research profile

About

Researcher in operating systems and machine learning systems, focused on efficient inference, reliable GPU sharing, and collaborative edge–cloud computing.

I am a master’s student at the Institute of Software, Chinese Academy of Sciences (ISCAS), and a research intern at Huawei 2012 Laboratories. I use this site to document research ideas, implementation notes, and lessons learned from building systems.

Education

  1. Sep 2025 – Present Institute of Software, Chinese Academy of Sciences M.S. in Computer Science and Technology
  2. Sep 2021 – Jun 2025 Nanjing University B.Eng. in Computer Science and Technology

Experience

  1. Jul 2026 – Present Huawei 2012 Laboratories · Central Research Institute Research Intern

Research Interests

  • Efficient inference for resource-constrained edge devices
  • Flexible, predictable, and reliable GPU spatial sharing
  • Communication and scheduling in collaborative edge–cloud systems

Selected Research

  1. Harmonizing PIM-Accelerated LLM Inference and Mobile Applications via Temporal-Spatial Isolation

    Zhenyuan Yang, Shicheng Deng, Zhao Zhang, Leibin Ni, Han Lin, Mengying Guo, Tao Wang, Erhu Feng, Mingyu Li, Haibo Chen

    Under Review 2026
  2. Determinism-Preserving GPU Spatial Sharing with Vitamin-E

    Zhenyuan Yang, Wenxin Zheng, Mingyu Li, Haibo Chen

    Under Review arXiv:2603.15042 2026
  3. Towards Large Language Model-Friendly APIs

    Yuan Wang, Zhenyuan Yang, Zhanbo Wang, Mingyu Li, Zhilin Wu, Haibo Chen

    Published ACM SIGOPS Operating Systems Review 59(1):17–23 2025

Awards

  • First Place, ACM Student Research Competition at SOSP
  • Outstanding Graduate, Nanjing University
  • Outstanding Student, Nanjing University

Projects

Skills

Programming
C/C++, Python, Java
Systems & tooling
Linux, Docker, CMake, GDB, Git
ML systems
PyTorch, DeepSpeed, TensorRT, CUDA

Personal Interests

  • Dogs, especially medium and large breeds
  • Basketball, especially the NBA

Contact