=== NVIDIA TensorRT for RTX ===

NVIDIA® TensorRT™ for RTX (TensorRT-RTX) is an inference optimization library dedicated for deploying AI inference on NVIDIA GeForce RTX GPUs. It is a great choice for developers building applications that must run on Windows or Linux PCs, laptops, or workstations. Many inference frameworks exist today ranging from cross-vendor solutions for broader compatibility but lack performance; to hardware specific libraries for peak performance but require developers to optimize every model for every target GPU thereby complicating deployment.

For more information about TensorRT-RTX, visit https://developer.nvidia.com/tensorrt-rtx.

Online documentation can be found at https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/index.html.

For details on TensorRT-RTX's license agreement, visit https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/reference/sla.html.


=== References ===

Release Notes: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/getting-started/release-notes.html
Support Matrix: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/getting-started/support-matrix.html
Installation Guide: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/installing-tensorrt-rtx/installation-overview.html
C++ API: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/_static/cpp-api/index.html
Python API: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/_static/python-api/index.html
