CUDA platform
CUDA is NVIDIA’s GPU computing platform, including programming interfaces, compilers, libraries and development tools. The toolkit is a distribution of development components; the GPU driver is a separate part of the installed stack.
How it works
An application may load a runtime library, call the driver, and execute precompiled or just-in-time compiled kernels. A Python package can bundle some CUDA libraries without bundling a compiler or the host’s kernel driver.
Work through an example
A machine can run a framework wheel with bundled runtime libraries even when nvcc is absent. Building a custom extension can then fail because that operation needs additional development tools.
Where the term can mislead
The CUDA version shown by nvidia-smi describes driver support. It does not inventory every toolkit or framework library installed on the machine.
Connect the idea
Take it into practice
Continue with the existing concept, apply it to an interview problem, or follow a course lesson. Access requirements are shown before you open a page.
New to GPUs? Start with the free execution-model concept.
Sources and scope
Examples here are teaching calculations, not measured GPU performance. Consult the linked documentation for the exact device, instruction and tool version. Source review: 25 October 2026.