Presenter

Yonghua Zhang received his Ph.D. degree from the School of Computer Science and Technology at Beihang University in 2023. He joined the High-Performance Computing Institute at the Department of Computer Science and Engineering, Tsinghua University, as a postdoctoral researcher in 2023. His research interests include AI model compression and compiler optimization, particularly for convolutional neural networks (CNNs) and large language models (LLMs) on GPUs. He current focuses on quantifying LLM models and optimizing compiler backends for performance, portability, and productivity.