I am Shulai Zhang, a research scientist at Huawei’s 2012 lab. I received my Ph.D. degree in Computer Science from Shanghai Jiao Tong University, supervised by Prof. Quan Chen. My research interests lie in optimizing AI systems on modern hardware, leveraging techniques including scheduling/compiling/resource-managing. I am now focusing on building data-centric OS infrastructure tailored for LLM/RL systems. Prior to joining Huawei, I had a wonderful experience at Bytedance Seed. Feel free to reach out if you are interested in potential collaboration!
Experiences
- 2024.07 - 2025.06, Research Intern - ByteDance Seed, contributed to several open-sourced projects, verl, vllm, Flux
- 2019.07 - 2020.05, Research Intern - Georgia Institute of Technology, involved in several PoW blockchain projects.
- 2016.09 - 2020.06, Bachelor - Information Engineering, Shanghai Jiao Tong University.
Publications
Published
- ATC 2025Shulai Zhang, Ao Xu, Quan Chen, Han Zhao, Weihao Cui, Zhen Wang, Yan Li, Limin Xiao, Minyi Guo. Efficient Performance-Aware GPU Sharing with Compatibility and Isolation through Kernel Space Interception.
- MLSys 2025Shulai Zhang, Ningxin Zheng, Haibin Lin, Ziheng Jiang, Wenlei Bao, Chengquan Jiang, Qi Hou, Weihao Cui, Size Zheng, Li-Wen Chang, Quan Chen, Xin Liu. Comet: Fine-grained computation-communication overlapping for mixture-of-experts.
- TACO 2025Yifu He, Han Zhao, Weihao Cui, Shulai Zhang, Quan Chen, Minyi Guo. Arachine: Optimizing distributed parallel applications with reduced inter-process communication.
- EuroSys 2025Shulai Zhang, Quan Chen, Weihao Cui, Han Zhao, Chunyu Xue, Zhen Zheng, Wei Lin, Minyi Guo. Improving GPU Sharing Performance through Adaptive Bubbleless Spatial-Temporal Sharing.
- SoCC 2023Binghao Chen, Han Zhao, Weihao Cui, Yifu He, Shulai Zhang, Quan Chen, Zijun Li, Minyi Guo. Maximizing the Utilization of GPUs Used by Cloud Gaming through Adaptive Co-location with Combo.
- ICS 2022Shulai Zhang, Weihao Cui, Quan Chen, Zhengnian Zhang, Yue Guan, Jingwen Leng, Chao Li, Minyi Guo. PAME: precision-aware multi-exit DNN serving for reducing latencies of batched inferences.
- ICPP 2021Shulai Zhang, Zirui Li, Quan Chen, Wenli Zheng, Jingwen Leng, Minyi Guo. Dubhe: Towards data unbiasedness with homomorphic encryption in federated learning client selection.
- ICASSP 2020Shulai Zhang, Xiaoli Ma. A General Difficulty Control Algorithm for Proof-of-Work Based Blockchains.
- SPAWC 2020Kaiwen Zheng, Shulai Zhang, Xiaoli Ma. Difficulty Prediction for Proof-of-Work Blockchains.
- Globecom 2019Shulai Zhang, Meixia Tao, Zhiyong Chen. Exploiting Caching and Prediction to Promote User Experience for a Real-time Wireless VR Service.
Preprint
- Arxiv PreprintShulai Zhang, Ao Xu, Quan Chen, Han Zhao, Weihao Cui, Ningxin Zheng, Haibin Lin, Xin Liu, Minyi Guo. Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution.
- Arxiv PreprintChunyu Xue, Weihao Cui, Han Zhao, Quan Chen, Shulai Zhang, Pengyu Yang, Jing Yang, Shaobo Li, Minyi Guo. A codesign of scheduling and parallelization for large model training in heterogeneous clusters.
- Arxiv PreprintHan Zhao, Weihao Cui, Quan Chen, Shulai Zhang, Zijun Li, Jingwen Leng, Chao Li, Deze Zeng, Minyi Guo. Towards fast setup and high throughput of GPU serverless computing.
Projects
- 2024, Performance isolation tools for multi-tenant NPU, Institute of Computing Technology, Chinese Academy of Sciences.
- 2023, Kernel-space virtualization for GPU sharing, Lenovo.
- 2023, Resource management and compilation co-design to optimize AI model performance, Alibaba Group.