Boning Huangfu

I am a Computer Science undergraduate in the John Class at Zhiyuan College, Shanghai Jiao Tong University. I am a member of the Emerging Parallel Computing Center (EPCC), advised by Prof. Chen Chen. My research interests lie in machine learning systems and large language model inference, particularly in efficient LLM serving, SLO-aware scheduling, heterogeneous GPU resource management, and KV-cache management.

My recent work focuses on building efficient and predictable serving systems for agentic LLM workloads. I am currently a research intern at Microsoft Research Asia’s Vancouver Lab, working on LLM inference systems under the supervision of senior researchers Tao Zhang and Jiamin Li.