TensorRT 7.2: What’s New

TensorRT 7.2 is packed with new optimizations that accelerate video-based workloads such as web conferencing and content streaming.


  • Optimizations for high-quality video effects such as live virtual background, delivering 30X performance vs CPUs
  • New Optimizations in RNNs, speeds up applications such as Fraud & Anomaly detection by 2x
  • Fully Connected Layer Optimizations, resulting upto 250% faster inference for Recommenders and MLPs

TensorRT 7.2 is available now.

Introductory Resources

Introductory Blog

Learn how to apply TensorRT optimizations and deploy a PyTorch model to GPUs.

Read Blog

Introductory Webinar

Build a sample TensorRT application that detects common objects in images from scratch.

Watch Webinar

Pre-Trained Models

Download pre-trained models optimized for TensorRT to get started quickly.

Click Here

Additional TensorRT Resources

Conversational AI

Image and Video

Recommendation Systems

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.