Di Wu

Di Wu is a director of Deep Learning Algorithm and Software at NVIDIA, leading a team focusing on deep learning model compression algorithms and software engineering. Di joined NVIDIA through the acquisition of OmniML, Inc., where he was the co-founder and CEO. Before that, he was an ML engineer at Meta working on PyTorch inference systems. He received his PhD in Computer Science from UCLA, and bachelor’s degree from Tsinghua University.
Di Wu

Posts by Di Wu

Generative AI

Accelerate Generative AI Inference Performance with NVIDIA TensorRT Model Optimizer, Now Publicly Available

In the fast-evolving landscape of generative AI, the demand for accelerated inference speed remains a pressing concern. With the exponential growth in model... 9 MIN READ