I am using the package llama-cpp-python for one of my projects. And this package has the option to install cuda support through a cmake argument which is done as so through the terminal.
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
How do I incorporate this when I am working through Pycharm? I know the file->settings method to install packages but I am not sure how to include the cmake argument.