RTX Neural Shading (RTXNS) also known as RTX Neural Shaders, is intended as a starting point for developers interested in bringing Machine Learning (ML) to their graphics applications. It provides a number of examples to help the reader understand how to train their own neural networks and then use those models to perform inference alongside their normal graphics rendering.
RTXNS uses the Slang shading language and it utilises the Vulkan Cooperative Vectors extension to provide access to the GPUs ML acceleration.
A number of examples are included which build upon each other from a simple inference example to more complex examples showing how to train a neural network to represent a shader or a texture. Helper functions to facilitate building your own neural networks are also included.
Alongside the core samples is a SlangPy sample to demonstrate how to use python and SlangPy for fast iteration and development of neural networks which can then be integrated into RTXNS for inference.
When exploring RTXNS, it is assumed that the reader is already familiar with ML and neural networks.
GPU must support the Vulkan VK_NV_cooperative_vector extension (minimum NVIDIA RTX 20XX) | CMake v3.24.3 | Vulkan SDK 1.3.296.0 | VS 2022 | Slang v2025.3.3 | Driver ≥ 572.16
| Directory | Details |
|---|---|
| /assets | Asset files for samples |
| /docs | Documentation for showcased tech |
| /samples | Samples showcasing usage of MLPs |
| /external/donut | Framework used for the examples |
| /external | Helper dependencies for the examples |
| /src | Helper and utility functions |
- Quick start guide for building and running the neural shading samples.
- Library usage guide for using helper functions
This project uses Slang and the Vulkan CoopVector extensions. The following links provide more detail on these, and other technologies which may help the reader to better understand the relevant technologies, or just to provide further reading.
RTXNS is actively being developed. Please report any issues directly through the GitHub issue tracker, and for any information or suggestions contact us at [email protected]
Use the following BibTex entry to cite the usage of RTXNS in published research:
@online{RTXNS,
title = {{{NVIDIA}}\textregistered{} {RTXNS}},
author = {{NVIDIA}},
year = 2025,
url = {https://github.com/NVIDIA-RTX/RTXNS},
urldate = {2025-02-03},
}See LICENSE.md