Jinwei Yao

Background

I am currently in the first year at UIUC, pursuing a (research-based) Master of Science in Computer Science(MSCS). My advisor is Prof.Jiaxuan You.

Before my journey at UIUC, I spent one year at EPFL as a felloship PhD student in distributed systems, where I laid my academic foundations. Leaving peaceful and beautiful Switzerland is a hard decision: after one year of thinking and discussion with my career mentor Prof. Katerina Argyraki, I followed my heart to explore ML System research. In Zhejiang University, I obtained my Bachelor's degree in Electronic Science and Technology, with Outstanding Thesis Award for designing FPGA subsystem for GNN acceleration, where was the start of my MLSys research. During my ML System research journey, I was lucky to work with wonderful advisors-- Prof. Zeke Wang(Zhejiang University), Prof. Tao Lin(Westlake University), and Prof. Binhang Yuan(HKUST).

At UIUC, my research focuses on Gen-AI Systems, like LLM inference efficiency. I am also interested in bringing distributed systems/database systems with LLMs.

Research Interest

I am intersted in machine learning systems (ML System), especially system designs for LLMs. My primary goal is to provide efficient, cheap and robust system services for real-world LLM applications. To achieve this goal, I identified three main challenges:

Challenge1 LLM Inference Efficiency
How to provide cheap and fast LLM inference service.

Challenge2 LLM Training Efficiency
How to provide efficient and robust LLM training.

Challenge3 Trade-off between service-level-objects (SLOs) in ML and System
How to do trade-offs between machine learning metrics (accuracy, PPL, etc) and system metrics (latency, throughtputs)

Miscellaneous

I am active in sharing paper readings on my another Github Blog and Zhihu(知乎). I like 🏀, 💪, 📚, 🐱, and 🎬.