Po-Han Huang

Po-Han Huang is a deep learning software engineer at NVIDIA, where he has spent over six years accelerating the inference of trained deep neural network models through TensorRT and CUDA optimizations. He holds a master's degree in electrical and computer engineering from the University of Illinois at Urbana-Champaign. His expertise spans deep learning acceleration, computer vision, and GPU architectures.
Avatar photo

Posts by Po-Han Huang

Data Center / Cloud

Blackwell Breaks the 1,000 TPS/User Barrier With Meta’s Llama 4 Maverick

NVIDIA has achieved a world-record large language model (LLM) inference speed. A single NVIDIA DGX B200 node with eight NVIDIA Blackwell GPUs can achieve over... 9 MIN READ