GSplat documentation

2025-12-15

1 min read time

Applies to Linux

GSplat (Gaussian splatting) is an open-source library for GPU-accelerated differentiable rasterization of 3D Gaussians with Python bindings that is part of the AMD ROCm™ Simulation Domain toolkit (ROCm-Simulation).

This ROCm-enabled release of GSplat is built on top of PyTorch for AMD ROCm, enabling innovators in computer graphics, machine learning, and 3D vision to leverage GPU acceleration with AMD Instinct™ GPUs. With GSplat, you can build, research, and innovate with Gaussian splatting.

The GSplat public repository is located at ROCm/gsplat.

Install

• Install GSplat

Examples

• GSplat examples

Reference

• GSplat API reference

• Benchmarking

• Profiling the library

To contribute to the documentation, refer to Contribute to GSplat.

You can find licensing information on the Licensing page.