Ivan Yin

Ivan Yin (Wenzhi Yin) is a senior computer architect engineer specializing in GPU compiler engineering and high-performance deep learning. He graduated from Shanghai Jiao Tong University. He has expertise in compiler development for NVIDIA CUDA Tile Programming, where he maps high-level tensor operations to efficient GPU machine code through automated code generation for modern GPU architectures. Beyond compiler engineering, he has experience in high-performance deep learning kernel development and performance tuning.
Avatar photo

Posts by Ivan Yin

Decorative image.
Developer Tools & Techniques

Tuning Flash Attention for Peak Performance in NVIDIA CUDA Tile

In this post, we dive into one of the most critical workloads in modern AI: Flash Attention, where you’ll learn: How to implement Flash Attention using NVIDIA... 20 MIN READ