Vinh Nguyen

Vinh Nguyen is a deep learning engineer and data scientist, having published more than 50 scientific articles attracting more than 2500 citations. At NVIDIA, his work spans a wide range of deep learning and AI applications, including speech, language and vision processing, and recommender systems.

Posts by Vinh Nguyen

Technical Walkthrough 0

Optimizing T5 and GPT-2 for Real-Time Inference with NVIDIA TensorRT

TensorRT 8.2 optimizes HuggingFace T5 and GPT-2 models. You can build real-time translation, summarization, and other online NLP apps. 9 MIN READ
Technical Walkthrough 2

Boosting NVIDIA MLPerf Training v1.1 Performance with Full Stack Optimization

In MLPerf training v1.1, we optimized across the entire stack including hardware, system software, libraries, and algorithms. 22 MIN READ
Technical Walkthrough 0

Introducing NVIDIA Riva: A GPU-Accelerated SDK for Developing Speech AI Applications

Learn about the Riva SDK and its use in developing speech AI applications. We also discuss pretrained models in NGC, TAO Toolkit for transfer learning. 7 MIN READ
Technical Walkthrough 0

Accelerating Embedding with the HugeCTR TensorFlow Embedding Plugin

The NVIDIA Merlin recommendation system framework introduces an optimized embedding implementation that is up to 8x more performant and is available as a TensorFlow plugin. 12 MIN READ
Technical Walkthrough 0

Continuously Improving Recommender Systems for Competitive Advantage Using NVIDIA Merlin and MLOps

This posts shares how NVIDIA Merlin components fit into a complete MLOps pipeline to operationalize a recommendation system, and continuously deliver improvements in production. 12 MIN READ
Technical Walkthrough 1

MLPerf v1.0 Training Benchmarks: Insights into a Record-Setting NVIDIA Performance

Learn about some of the major optimizations made to the NVIDIA platform that contributed to the nearly 7x increase in performance since the first MLPerf training benchmark. 31 MIN READ