Environment Variables#

Runtime Environment Variables#

  • CUDA_PYTHON_CUDA_PER_THREAD_DEFAULT_STREAM : When set to 1, the default stream is the per-thread default stream. When set to 0, the default stream is the legacy default stream. This defaults to 0, for the legacy default stream. See Stream Synchronization Behavior for an explanation of the legacy and per-thread default streams.

  • CUDA_PYTHON_DISABLE_MAJOR_VERSION_WARNING : When set to 1, suppresses warnings about CUDA major version mismatches between cuda-bindings and the installed driver.

Build-Time Environment Variables#

  • CUDA_PATH or CUDA_HOME: Specifies the location of the CUDA Toolkit. If both are set, CUDA_PATH takes precedence.

    Note

    The CUDA_PATH > CUDA_HOME priority is determined by cuda-pathfinder. Earlier versions of cuda-pathfinder (before 1.5.0) used the opposite order (CUDA_HOME > CUDA_PATH). See the cuda-pathfinder 1.5.0 release notes for details and migration guidance.

  • CUDA_PYTHON_PARSER_CACHING : bool, toggles the caching of parsed header files during the cuda-bindings build process. If caching is enabled (CUDA_PYTHON_PARSER_CACHING is True), the cache path is set to ./cache_<library_name>, where <library_name> is derived from the cuda toolkit libraries used to build cuda-bindings.

  • CUDA_PYTHON_PARALLEL_LEVEL (previously PARALLEL_LEVEL) : int, sets the number of threads used in the compilation of extension modules. Not setting it or setting it to 0 would disable parallel builds.