Hi, I’m Huanyu Yang (杨环宇), an undergraduate at Dalian University of Technology.

I work on LLM agents. My interests center on agent systems and post-training, and I spend a fair amount of time with the infrastructure that makes them run: reinforcement learning, vLLM, and vLLM-omni.

This blog is where I write up what I’m reading and building: paper notes, implementation deep-dives, and the things I wish someone had explained to me earlier.

Focus

• Agent development
• Post-training
• Inference and RL infrastructure (vLLM / vLLM-omni)

Contact

• Email: 3868850350@qq.com / yhy3868850350@gmail.com
• GitHub: QingZhou-YangHY