This functionality is currently in an experimental phase and may be used for evaluation purposes but should not be deployed in a production environment.
To enable check the box in Settings:
The DirectML hardware-accelerated DirectX 12 library for machine learning requires any DirectX 12 capable device.
NVIDIA Kepler (GTX 600 series) and above
AMD GCN 1st Gen (Radeon HD 7000 series) and above
Intel Haswell (4th-gen core) HD Integrated Graphics and above
Qualcomm Adreno 600 and above
DirectML is compatible with Windows 10, version 1903 and newer.
NVIDIA CUDA can be enabled in Linux (tested for Ubuntu 20.04) using the script
enable-cuda.sh found under the Breeze/Runtime directory. This will download the required library files. By downloading and using the software, you agree to fully comply with the terms and conditions of the https://docs.nvidia.com/cuda/eula/index.html . More information concerning the requirements see: https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements
When applicable to following order of priority is used:
DirectML1 or CUDA2
Generic CPU (MLAS)
Enables hardware accelerated computation on Nvidia CUDA-enabled GPUs. Only available on Linux.
Supported matrix (see https://docs.nvidia.com/deploy/cuda-compatibility/index.html#support-hardware) :
Linux x86_64 Driver Version
Windows x86_64 Driver Version
1 Windows Only
2 Linux Only