Shengliang Xu

Shengliang Xu is a senior deep learning engineer on the NVIDIA Algorithmic Model Optimization team focused on end-to-end optimization of deep learning model inference on NVIDIA GPU platforms. His research and development interests span model and inference system optimization of large language models and large generative models. Shengliang holds an M.S. degree in computer science from University of Washington, where he dropped out the Ph.D. program. He holds another M.S. degree and a B.S. degree both in computer science from Shanghai Jiao Tong University.
Avatar photo

Posts by Shengliang Xu

An image of an NVIDIA H200 Tensor Core GPU.
Generative AI / LLMs

NVIDIA H200 Tensor Core GPUs and NVIDIA TensorRT-LLM Set MLPerf LLM Inference Records

Generative AI is unlocking new computing applications that greatly augment human capability, enabled by continued model innovation. Generative AI... 11 MIN READ