haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

cmake: revert CUDA arch default to 52, 61 if f16 (#1959)

Browse source
This commit is contained in:
Johannes Gäßler 2023-06-21 23:49:25 +02:00 committed by GitHub
parent fb98254f99
commit bbca06e269
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
CMakeLists.txt
View file

@ -250,6 +250,15 @@ if (LLAMA_CUBLAS)
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
endif()
if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
if (LLAMA_CUDA_DMMV_F16)
set(CMAKE_CUDA_ARCHITECTURES "61") # needed for f16 CUDA intrinsics
else()
set(CMAKE_CUDA_ARCHITECTURES "52") # lowest CUDA 12 standard
endif()
endif()
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
else()
message(WARNING "cuBLAS not found")
endif()
@ -493,22 +502,6 @@ if (BUILD_SHARED_LIBS)
endif()
endif()
if (GGML_SOURCES_CUDA)
message(STATUS "GGML CUDA sources found, configuring CUDA architecture")
set_property(TARGET ggml PROPERTY CUDA_ARCHITECTURES "native")
set_property(TARGET ggml PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
set_property(TARGET ggml_static PROPERTY CUDA_ARCHITECTURES "native")
set_property(TARGET ggml_static PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
if (BUILD_SHARED_LIBS)
set_property(TARGET ggml_shared PROPERTY CUDA_ARCHITECTURES "native")
set_property(TARGET ggml_shared PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
endif()
set_property(TARGET llama PROPERTY CUDA_ARCHITECTURES "native")
endif()
#
# programs, examples and tests