xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 08:04:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Flash attention arches not getting set properly (#9062)

Browse Source
This commit is contained in:
Lucas Wilkinson 2024-10-04 11:43:15 -04:00 committed by GitHub
parent 3d826d2c52
commit 22482e495e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
CMakeLists.txt
View File

@ -482,6 +482,17 @@ if (NOT VLLM_TARGET_DEVICE STREQUAL "cuda")
return()
endif ()
# vLLM flash attention requires VLLM_GPU_ARCHES to contain the set of target
# arches in the CMake syntax (75-real, 89-virtual, etc), since we clear the
# arches in the CUDA case (and instead set the gencodes on a per file basis)
# we need to manually set VLLM_GPU_ARCHES here.
if(VLLM_GPU_LANG STREQUAL "CUDA")
foreach(_ARCH ${CUDA_ARCHS})
string(REPLACE "." "" _ARCH "${_ARCH}")
list(APPEND VLLM_GPU_ARCHES "${_ARCH}-real")
endforeach()
endif()
#
# Build vLLM flash attention from source
#