Jian Hu

Jian Hu is a senior system software engineer at NVIDIA working for TensorRT and TensorRT Edge-LLM. His work includes performance analysis and optimization for deep learning compilers, new performance scheduling technique research, and LLM inference performance improvement. Jian holds a master's degree in Computer Science from University of Southern California and a bachelor’s degree in Computer Science from Huazhong University of Science and Technology.
Avatar photo

Posts by Jian Hu

Edge Computing Oct 23, 2026

Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2

The Global Performance Tuner is a feature for automatic performance tuning released in NVIDIA TensorRT 11.1. It provides automatic, accuracy-aware and... 12 MIN READ
Edge Computing Oct 23, 2026

Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1

Deploying a trained neural network involves more than translating each operator into a GPU kernel. It is a compilation problem with many legitimate answers. For... 14 MIN READ