CUDA on Arm
The CUDA® Toolkit for Arm provides a development environment for creating high performance GPU-accelerated applications on the Arm server platform. With the CUDA Toolkit, you can develop, optimize and deploy your applications on GPU-accelerated Arm systems. The toolkit includes GPU-accelerated libraries, debugging and optimization tools, a C/C++ compiler, and the CUDA runtime and drivers to deploy your application.
CUDA is now supported on Arm servers starting with CUDA 11. To download production releases of CUDA for Arm, visit the CUDA Toolkit download page.