20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix][CI/Build] Fix docker build where CUDA archs < 7.0 are being detected (#9254)

Browse Source
This commit is contained in:
Lucas Wilkinson 2024-10-11 15:57:39 -04:00 committed by GitHub
parent 8baf85e4e9
commit de9fb4bef8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
CMakeLists.txt
View File

@ -144,27 +144,32 @@ else()
endif()
#
# For cuda we want to be able to control which architectures we compile for on
# a per-file basis in order to cut down on compile time. So here we extract
# the set of architectures we want to compile for and remove the from the
# CMAKE_CUDA_FLAGS so that they are not applied globally.
#
if(VLLM_GPU_LANG STREQUAL "CUDA")
#
# For cuda we want to be able to control which architectures we compile for on
# a per-file basis in order to cut down on compile time. So here we extract
# the set of architectures we want to compile for and remove the from the
# CMAKE_CUDA_FLAGS so that they are not applied globally.
#
clear_cuda_arches(CUDA_ARCH_FLAGS)
extract_unique_cuda_archs_ascending(CUDA_ARCHS "${CUDA_ARCH_FLAGS}")
message(STATUS "CUDA target architectures: ${CUDA_ARCHS}")
# Filter the target architectures by the supported supported archs
# since for some files we will build for all CUDA_ARCHS.
cuda_archs_loose_intersection(CUDA_ARCHS
"${CUDA_SUPPORTED_ARCHS}" "${CUDA_ARCHS}")
message(STATUS "CUDA supported target architectures: ${CUDA_ARCHS}")
else()
#
# For other GPU targets override the GPU architectures detected by cmake/torch
# and filter them by the supported versions for the current language.
# The final set of arches is stored in `VLLM_GPU_ARCHES`.
#
override_gpu_arches(VLLM_GPU_ARCHES
${VLLM_GPU_LANG}
"${${VLLM_GPU_LANG}_SUPPORTED_ARCHS}")
endif()
#
# Override the GPU architectures detected by cmake/torch and filter them by
# the supported versions for the current language.
# The final set of arches is stored in `VLLM_GPU_ARCHES`.
#
override_gpu_arches(VLLM_GPU_ARCHES
${VLLM_GPU_LANG}
"${${VLLM_GPU_LANG}_SUPPORTED_ARCHS}")
#
# Query torch for additional GPU compilation flags for the given
# `VLLM_GPU_LANG`.