I am a second-year Master’s student of Computer Science and Technology at Sun Yat-sen University, under the supervision of Prof. Xianwei Zhang. Previously I completed my Bachelor’s degree at South China University of Technology (SCUT).

My research focuses on building practical, scalable, and efficient systems for machine learning (MLSys). I am an active contributor to open-source projects including vLLM and veRL.

🛠️ Skills

Programming Languages: Python, C++, Shell
Frameworks: PyTorch, VLLM, SGLang, verl, slime
Tools: Git, Linux, Docker, Nsight System

🔥 News

2026.01: Joined Tencent as a research intern.
2025.09: 🎉🎉 My first paper DynaPipe has been accepted by NeurIPS 2025.
2025.08: Joined SenseTime as a research intern.

📝 Publications

DynaPipe: Dynamic Layer Redistribution for Efficient Serving of LLMs with Pipeline Parallelism
Hongxin Xu^#, Tianyu Guo^#, Xianwei Zhang

Bullet: Boosting GPU Utilization for LLM Serving via Dynamic Spatial-Temporal Orchestration
Zejia Lin, Hongxin Xu, Guanyi Chen, Zhiguang Chen, Yutong Lu, and Xianwei Zhang.

^# Equal contribution

💻 Internships

2026.01 – now, RL Infra Intern (Qingyun Program), Tencent HunYuan, Shenzhen.
Supervised by Guangming Sheng.
2025.08 – 2025.12, RL Infra Research Intern, SenseTime, Shenzhen.
Supervised by Shihao Bai and Ruihao Gong.

🎖 Honors and Awards

2025.11 Tencent Special Scholarship
2025.10 NeurIPS 2025 Scholar Award
2025,09 First-Class Scholarship, Sun Yat-sen University
2024.09 Second-Class Scholarship, Sun Yat-sen University
2023.09 & 2022.09 Second-Class Scholarship, South China University of Technology

📖 Educations