.. module:: cuda.bindings
Released on Oct 9, 2025
- This is the last release that officially supports Python 3.9.
- Python 3.14 is supported.
- Experimental free-threaded builds for Python 3.13/3.14 are made available. Any bugs can be reported to our GitHub repo. More details are available in our :ref:`support` docs.
- Migrated wheel dependencies from individual NVIDIA packages to the
cuda-toolkitmetapackage for improved dependency resolution and version constraints. - Automatic CUDA library path detection based on
CUDA_HOME, eliminating the need to manually setLIBRARY_PATHenvironment variables for installation. - The
[all]optional dependencies now usecuda-toolkitwith appropriate extras instead of individual packages. The NVCC compiler is no longer automatically installed withpip install cuda-python[all]as it was previously included only to access the NVVM library, which now has its own dedicated wheel. Users who need the NVCC compiler should explicitly install it withpip install cuda-toolkit[nvcc]==X.Ywith the appropriate version for their needs. - The Python overhead of calling functions in CUDA bindings in
driver,runtimeandnvrtchas been reduced by approximately 30%. - On Windows, the
pywin32dependency has been removed. The necessary Windows API functions are now accessed directly. - Updated the
cuda.bindings.runtimemodule to statically link against the CUDA Runtime library from CUDA Toolkit 13.0.1. cyruntime.getLocalRuntimeVersionnow uses pathfinder to find the CUDA runtime.
- Restoring the :func:`~driver.cuCheckpointProcessRestore` API removed by mistake.
- Updating from older versions (v12.6.2.post1 and below) via
pip install -U cuda-pythonmight not work. Please do a clean re-installation by uninstallingpip uninstall -y cuda-pythonfollowed by installingpip install cuda-python.