Infrastructure engineer focused on LLM inference systems.
- M.S. Computer Science — Shanghai Jiao Tong University
- B.S. Computer Science — Harbin Institute of Technology
- 2 yrs at Alibaba
Focus Areas: LLM Inference / GPU Performance
Currently contributing to vllm — KV cache transfer, scheduler optimization, and hybrid KV cache management (HMA).
See detail at my vllm contributions
📫 ethan.fengch [at] gmail.com

