diff --git a/CMakeLists.txt b/CMakeLists.txt index a53a8575..d1956f3d 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -169,12 +169,12 @@ endif() # # Use FetchContent for C++ dependencies that are compiled as part of vLLM's build process. -# Configure it to place files in vllm/.deps, in order to play nicely with sccache. +# setup.py will override FETCHCONTENT_BASE_DIR to play nicely with sccache. +# Each dependency that produces build artifacts should override its BINARY_DIR to avoid +# conflicts between build types. It should instead be set to ${CMAKE_BINARY_DIR}/. # include(FetchContent) -get_filename_component(PROJECT_ROOT_DIR "${CMAKE_CURRENT_SOURCE_DIR}" ABSOLUTE) -file(MAKE_DIRECTORY "${FETCHCONTENT_BASE_DIR}") -set(FETCHCONTENT_BASE_DIR "${PROJECT_ROOT_DIR}/.deps") +file(MAKE_DIRECTORY ${FETCHCONTENT_BASE_DIR}) # Ensure the directory exists message(STATUS "FetchContent base directory: ${FETCHCONTENT_BASE_DIR}") # @@ -509,6 +509,8 @@ else() GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git GIT_TAG 013f0c4fc47e6574060879d9734c1df8c5c273bd GIT_PROGRESS TRUE + # Don't share the vllm-flash-attn build between build types + BINARY_DIR ${CMAKE_BINARY_DIR}/vllm-flash-attn ) endif() diff --git a/setup.py b/setup.py index d1f4b7f1..8abeb0ba 100644 --- a/setup.py +++ b/setup.py @@ -157,6 +157,14 @@ class cmake_build_ext(build_ext): # on subsequent calls to python. cmake_args += ['-DVLLM_PYTHON_PATH={}'.format(":".join(sys.path))] + # Override the base directory for FetchContent downloads to $ROOT/.deps + # This allows sharing dependencies between profiles, + # and plays more nicely with sccache. + # To override this, set the FETCHCONTENT_BASE_DIR environment variable. + fc_base_dir = os.path.join(ROOT_DIR, ".deps") + fc_base_dir = os.environ.get("FETCHCONTENT_BASE_DIR", fc_base_dir) + cmake_args += ['-DFETCHCONTENT_BASE_DIR={}'.format(fc_base_dir)] + # # Setup parallelism and build tool #