He worked as a visiting scholar at Purdue University, advised by Prof. Y. Charlie Hu from 2024 to 2025. He received his Ph.D. degree in Computer Science (Zhiyuan Honored Program) from Shanghai Jiao Tong University in 2025, advised by Prof. Haibing Guan. His general research interest is in LLM systems, cloud computing, and mobile systems.

More recently, his research has focused on:

1. LLM inference systems for edge & servers, with a focus on energy-efficiency: CORE [MLSys'26], SegMo [CVPR'26]

2. I/O virtualization systems for public cloud that are efficient, scalable, and manageable: HD-IOV [EuroSys'24], Un-IOV [IEEE TC'24], M3U [OSDI'26]

3. Cloud systems for AI workloads, with a focus on serverless and in-network offloading: P4KVS [SIGMOD'25], vCrypto [INFOCOM'24], QKPT [IEEE TDSC'21]

Previously, he received his B.S. degree in Computer Science and Technology (IEEE Pilot Class) also from Shanghai Jiao Tong University in 2019, advised by Prof. Haibing Guan.

Selected Publications

Please refer to Google Scholar for a complete list of publications.

[1]. Rethinking DVFS for Mobile LLMs: Unified Energy-Aware Scheduling with CORE

• Zongpu Zhang*, Pranab Dash*, Y. Charlie Hu, Qiang Xu, Jian Li, Haibing Guan (* equal contribution)

• The Ninth Annual Conference on Machine Learning and Systems (MLSys), 2026.

[2]. P4KVS: A Role-Replica Separation Offloading Method to Achieve In-Network Consistency for KV Stores Based on P4 Switches

• Haojuan Li, Zongpu Zhang, Chenzhen Ye, Ruohan Tang, Jian Li, Haibing Guan, Qiaoling Wang, and Pengpeng Zhou

• Proceedings of the ACM on Management of Data (SIGMOD), 2025.

[3]. HD-IOV: SW-HW Co-designed I/O Virtualization with Scalability and Flexibility for Hyper-Density Cloud

• Zongpu Zhang, Jiangtao Chen, Banghao Ying, Yahui Cao, Lingyu Liu, Jian Li, Xin Zeng, Junyuan Wang, Weigang Li, Haibing Guan

• The Nineteenth European Conference on Computer Systems (EuroSys), 2024.

[4]. Un-IOV: Achieving Bare-Metal Level I/O Virtualization Performance for Cloud Usage With Migratability, Scalability and Transparency

• Zongpu Zhang, Chenbo Xia, Cunming Liang, Jian Li, Chen Yu, Tiwei Bie, Roberts Martin, Daly Dan, Xiao Wang, Yong Liu, Haibing Guan

• IEEE Transactions on Computers (TC), 2024.

[5]. vCrypto: a Unified Para-Virtualization Framework for Heterogeneous Cryptographic Resources

• Shuo Shi, Chao Zhang, Zongpu Zhang, Hubin Zhang, Xin Zeng, Weigang Li, Junyuan Wang, Xiantao Zhang, Yibin Shen, Jian Li, Haibing Guan

• IEEE Conference on Computer Communications (INFOCOM), 2024.

[6]. QKPT: Securing Your Private Keys in Cloud With Performance, Scalability and Transparency

• Zongpu Zhang, Hubin Zhang, Junyuan Wang, Xiaokang Hu, Jian Li, Wenqian Yu, Ping Yu, Weigang Li, Bo Cui, Guodong Zhu, Kapil Sood, Brian Will, Haibing Guan

• IEEE Transactions on Dependable and Secure Computing (TDSC), 2021.

[7]. TACT [under review] 

[8]. LayerWeave [under review]

[9]. TIDE [under review]

[10]. SlideGraph [under review]

He was fortunate to collaborate on the following works:

• VLM serving system: SegMo [CVPR'26]

• Virtualization and serverless system: M3U [OSDI'26], Ephemera [TACO'25], SMore [TPDS'25], DEPT [under review], DAPS [under review]

• LLM algorithm and application: MentalGPT [TAFFC'26]

He used to work on following topics but not anymore:

• Video object tracking and segmentation: TWS-OVS [MM'18], HDDNN [TBD'18], ACGAN [MM'19], Object-guided [ICCV'19]

Professional Experience

1. Visiting Scholar @ Purdue University

   • 2024 - 2026, West Lafayette, IN, USA

   • Elmore Family School of Electrical and Computer Engineering

   • Advisor: Prof. Y. Charlie Hu

   • Role: AI-based system design for mobile LLM inferencing and distributed LLM serving.

2. Visiting Scholar @ Purdue University

   • 2023 - 2024, West Lafayette, IN, USA

   • Department of Computer Science

   • Advisor: Prof. Xuehai Qian

   • Role: Optimizing distributed LLM serving systems with forward- and backward-fused pipeline parallelism.

3. Research Intern @ Intel

   • 2020 - 2023, Shanghai, China

   • Network Platforms Group (NPG)

   • Advisor: Junyuan Wang and Xin Zeng

   • Role: I participated in developing Intel QAT driver and QAT engine for Intel KPT and Intel S-IOV technologies.

4. Research Intern @ Sensetime Research

   • Summer 2019, Shanghai, China

   • ADAS Team

   • Advisor: Guangliang Cheng 

   • Role: I explored Neural Architecture Search (NAS) algorithms for visual recognition in autonomous driving.

5. Research Intern @ Intel

   • Summer 2018, Shanghai, China

   • Data Center Group (DCG)

   • Advisor: Jason Dai (Intel Fellow)

   • Role: I prototyped a Computer Vision system using Intel BigDL library for a distributed AI agent that plays the FIFA football video game. Media 

Professional Services

Journal Reviewer

• Computer Networks (International Journal of Computer and Telecommunications Networking)

• IEEE Transactions on Sustainable Computing

• IEEE Transactions on Mobile Computing

• Transactions on Machine Learning Research

Conference Program Committee

• MLSys'26 Artifact Evaluation

Talks

• Feb 3, 2026, "Model-baesd RL for System Research"

  • Location: IntelliSys, Stevens Institute of Technology

• Feb 5, 2024, "I/O Virtualization for In-network Accelerators in Cloud -- Security, Efficiency, and Scalability"

  • Location: DSNL, Purdue University

• Jan 29, 2024, "Scalable I/O Virtualization for In-network Accelerators -- An example with Intel QAT accelerators".

  • Location: VT Security & Intelligence Lab, Virginia Tech

Awards

Student Awards

• 2019, Zhiyuan Honored Ph.D. Program (Top 2%), SJTU

• 2019, Excellent Bachelor’s Thesis Award (Top 1%), SJTU, Media (in zh-CN) 

• 2019, Zhang Xu Scholarship, SJTU

• 2019, Yang Yuanqing Scholarship, SJTU, Media (in zh-CN) 

• 2018, SenseTime Scholarship, Sensetime Inc.

• 2016,17,18, Academic Excellence Scholarship (three times), SJTU

Misc

• 2022, Winner (1st place) of the 2022 Fall NVIDIA DPU Hackathon in China, NVIDIA, Media (in zh-CN)