happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413)

This commit is contained in:
QDelta 2025-12-27 20:33:14 -05:00 committed by GitHub
parent 08566977a7
commit 4fd59e8427
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/CMakeLists.txt
View File

@ -37,14 +37,13 @@ if (CUDAToolkit_FOUND)
endif()
endif()
endif()
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
enable_language(CUDA)
# Replace any 12x-real architectures with 12x{a}-real. FP4 ptx instructions are not available in just 12x
if (GGML_NATIVE)
set(PROCESSED_ARCHITECTURES "")
if (CMAKE_CUDA_ARCHITECTURES_NATIVE)
if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES AND CMAKE_CUDA_ARCHITECTURES_NATIVE)
set(ARCH_LIST ${CMAKE_CUDA_ARCHITECTURES_NATIVE})
else()
set(ARCH_LIST ${CMAKE_CUDA_ARCHITECTURES})
@ -66,6 +65,7 @@ if (CUDAToolkit_FOUND)
endif()
endforeach()
endif()
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
file(GLOB GGML_HEADERS_CUDA "*.cuh")
list(APPEND GGML_HEADERS_CUDA "../../include/ggml-cuda.h")