Hi there, I'm Shengguang Zhu 👋

ML Systems Engineer | High-Performance Computing Enthusiast
Specializing in scalable RL Infrastructure and high-throughput LLM Inference.

I am a developer deeply passionate about AI Infrastructure, with a primary focus on Reinforcement Learning Frameworks and SGLang. My goal is to make distributed training and inference as fast and scalable as possible, diving deep into the intersection of machine learning and systems.

• RL Infrastructure: Building and optimizing reinforcement learning training and inference pipelines.
• SGLang & LLM Inference: Deeply engaged with SGLang to push the boundaries of LLM serving.
• Kernel Optimization: Designing and tuning high-performance custom kernels.
• Writing: I maintain 📚 MLsys-Note, an open space where I document my explorations, software notes, and code snippets on AI infrastructure.

Infinite progress.