Open leofang opened 2 weeks ago
I noted that due to the way we look up headers at run time, editable install (pip install -e .
) does not work.
I have opened a PR to address:
I believe we can get rid of
AFAIK we need
Issue tracking CCCL headers installation in cuda.parallel: https://github.com/NVIDIA/cccl/issues/2281 Issue tracking CMake improvements for CCCL/c: https://github.com/NVIDIA/cccl/issues/2235
Building
cuda.parallel
is quite brittle due to requirements from the C library. Through some patient trials and errors I discovered the following build-time dependencies are required:std::format
)Also I have to set the env var
CUDAARCHS
likeCUDAARCHS="86;89" pip install -v .
so that CMake knows which archs to build for, otherwise CMake also complains.Suggestions: