Viraat Chandra

Viraat Chandra is a deep learning performance engineer on the TensorRT team at Nvidia, focused on delivering world-class gen-AI inference performance results in MLPerf inference. He previously worked on recommender systems, applied AI, and auto-tuning, and has deep interest in AI-powered tools and methodologies in software development. Viraat holds a bachelor's degree in electrical engineering and computer science from the University of California, Berkeley.
Avatar photo

Posts by Viraat Chandra

Data Center / Cloud

NVIDIA Blackwell Ultra Sets New Inference Records in MLPerf Debut

As large language models (LLMs) grow larger, they get smarter, with open models from leading developers now featuring hundreds of billions of parameters. At the... 9 MIN READ