Google Scholar / Github / IEEE Xplore / ORCID / Linkedin / Contact

He is a fifth-year Ph.D. student advised by Prof. Haibing Guan and Prof. Jian Li at the Department of Computer Science, Shanghai Jiao Tong University. He finished the Bachelor’s degree at the Department of Computer Science, Shanghai Jiao Tong University in 2019.

Now he is a visiting scholar advised by Prof. Y. Charlie Hu at the School of Electrical and Computer Engineering, Purdue University. He was a visiting scholar advised by Prof. Xuehai Qian at School of Computer Science, Purdue University in 2023.

Update:

[01/19/2025] New blog posted: Mobile LLM on Android - Chapter 1

Research Interests

His research interests span machine learning systems, virtualization systems, and mobile computing. Prior to 2019, his work primarily focused on deep learning-based computer vision algorithms, resulting in several publications on top-tier AI/CV conferences. Since 2019, he has been focusing on cloud operating systems, aiming to develop more efficient, scalable, and manageable next-generation cloud infrastructures. He is currently working on DPU-offloaded remote memory systems and programmable switch-offloaded transaction processing systems. His research has covered a range of topics, including:

  • 🌟 Software-hardware co-designed I/O virtualization
  • 🌟 Hardware cryptography accelerators
  • 🌟 In-network offloading
  • 🌟 Cloud security

Since 2023, he has expanded his expertise in operating systems by exploring machine learning systems, with a particular emphasis on large language model (LLM) serving and inferencing on both server and mobile platforms.

His current research focuses on optimizing LLM fine-tuning and serving efficiency, as well as developing mobile LLM inference engines.

🔎 Selected Publications 🔍

(Please navigate to Google Scholar for a complete list of publications.)

  • [Eurosys'24] HD-IOV: serving >700 VMs with one NIC at bare-metal level performance. [Paper] [Artifact]

  • [INFOCOM'24] vCrypto: para-virtualized crypto accelerator. [Paper]

  • [IEEE TC'24] Un-IOV: migratable device passth-roughput system. [Paper]

  • [IEEE TDSC'21] QKPT: secure cloud KMS at rocket speed. [Paper]

Professional Experience

  • Reviewer for the 2024 International Journal of Computer and Telecommunications Networking

Industrial Experience

  • March, 2020 - March, 2023. Software Development Intern (NPG), Intel Asia-Pacific R&D Ltd.
  • Summer 2019. Research Intern (ADAS team), Sensetime Inc.
  • Summer 2018. Deep Learning Intern (DCG), Intel Asia-Pacific R&D Ltd.

Teaching Experience

  • 2020,21,22, Teaching assistant, EI313 Science and Technology Innovation, Shanghai Jiao Tong University

Honors and Award

  • 2019, Zhiyuan Honored Ph.D. Program, SJTU
  • 2019, Excellent Bachelor’s Thesis Award (Top 1%), SJTU
  • 2019, Zhang Xu Scholarship, SEIEE, SJTU
  • 2019, Yang Yuanqing Scholarship, SEIEE, SJTU
  • 2018, SenseTime Scholarship, Sensetime Inc.
  • 2016,17,18, Academic Excellence Scholarship (three times), SJTU