Terry Chen

Terry Chen is a principal engineer at NVIDIA. Prior to NVIDIA, he was VP of engineering at HippoML. As a co-author of AITemplate, he contributed to GPU optimization frameworks. His expertise encompasses large language models, AI agents, GPU inference optimization, and multi-modal AI applications.
Avatar photo

Posts by Terry Chen

Mixture of experts icons for attention kernels.
Generative AI Feb 12, 2025

Automating GPU Kernel Generation with DeepSeek-R1 and Inference Time Scaling

As AI models extend their capabilities to solve more sophisticated challenges, a new scaling law known as test-time scaling or inference-time scaling is... 6 MIN READ