About

I'm Shengguang Zhu — an ML systems engineer working on AI infrastructure, with a primary focus on reinforcement learning frameworks and LLM inference. I contribute to SGLang and FastDeploy, and my goal is to make distributed training and inference as fast and scalable as possible, diving into the intersection of machine learning and systems.

What I work on

• RL Infrastructure: Building and optimizing reinforcement learning training and inference pipelines.
• LLM Inference: Contributing to SGLang and FastDeploy, across the serving runtime and the kernels underneath it. SGLang · FastDeploy
• Router: Session and KV-cache aware routing, contributing to Dynamo. Dynamo
• Kernel Optimization: Designing and tuning high-performance custom kernels.
• Writing: Maintaining MLsys-Note, an open space for notes and code on AI infrastructure. MLsys-Note

Get in touch

Email is shengguangzhu@qq.com. For anything code-related, a GitHub issue or discussion on the relevant repository is faster. Corrections are welcome and get credited.

Infinite progress.