Make various updates and fixes:

- Add support for legacy CUDA versions; now compatible with CUDA 12.3 and newer
- Add support for NVRTC compilation
- Other fixes and code refactoring
This commit is contained in:
Ray Wang
2025-08-02 19:52:22 -07:00
parent aff9da0aba
commit d9c363f86f
36 changed files with 592 additions and 362 deletions

View File

@@ -18,8 +18,8 @@ find_package(CUDAToolkit REQUIRED)
find_package(pybind11 REQUIRED)
find_package(Torch REQUIRED)
set(CMAKE_CXX_STANDARD 20)
set(CMAKE_CUDA_STANDARD 20)
set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CUDA_STANDARD 17)
include_directories(deep_gemm/include third-party/cutlass/include third-party/cutlass/tools/util/include third-party/fmt/include)
include_directories(${CUDA_TOOLKIT_ROOT_DIR}/targets/x86_64-linux/include ${TORCH_INCLUDE_DIRS} ${PYTHON_INCLUDE_DIRS})