xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 08:55:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Use NVCC --compress-mode to reduce binary size by 30% #20694" (#20853)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-07-12 15:07:35 +09:00 committed by GitHub
parent 4afe687a82
commit b639327ad9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
CMakeLists.txt
View File

@ -171,16 +171,6 @@ if(NVCC_THREADS AND VLLM_GPU_LANG STREQUAL "CUDA")
list(APPEND VLLM_GPU_FLAGS "--threads=${NVCC_THREADS}")
endif()
#
# Set nvcc fatbin compression.
#
if(VLLM_GPU_LANG STREQUAL "CUDA")
if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
list(APPEND VLLM_GPU_FLAGS "-Xfatbin" "-compress-all" "-compress-mode=size")
endif()
endif()
#
# Use FetchContent for C++ dependencies that are compiled as part of vLLM's build process.
# setup.py will override FETCHCONTENT_BASE_DIR to play nicely with sccache.