mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 19:34:35 +00:00
f95caa7954
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-musa.Dockerfile platforms:linux/amd64 tag:full-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-musa.Dockerfile platforms:linux/amd64 tag:light-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-musa.Dockerfile platforms:linux/amd64 tag:server-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
* cmake pkg: find accelerate, openmp, memkind libs * cmake pkg: find BLAS libs * try BLAS_LIBRARIES instead * Add BLAS link opts * Add more link deps. and set GGML_ vars
179 lines
5.8 KiB
CMake
179 lines
5.8 KiB
CMake
set(LLAMA_VERSION @LLAMA_INSTALL_VERSION@)
|
|
set(LLAMA_BUILD_COMMIT @LLAMA_BUILD_COMMIT@)
|
|
set(LLAMA_BUILD_NUMBER @LLAMA_BUILD_NUMBER@)
|
|
set(LLAMA_SHARED_LIB @BUILD_SHARED_LIBS@)
|
|
|
|
set(GGML_STATIC @GGML_STATIC@)
|
|
set(GGML_NATIVE @GGML_NATIVE@)
|
|
set(GGML_LTO @GGML_LTO@)
|
|
set(GGML_CCACHE @GGML_CCACHE@)
|
|
set(GGML_AVX @GGML_AVX@)
|
|
set(GGML_AVX2 @GGML_AVX2@)
|
|
set(GGML_AVX512 @GGML_AVX512@)
|
|
set(GGML_AVX512_VBMI @GGML_AVX512_VBMI@)
|
|
set(GGML_AVX512_VNNI @GGML_AVX512_VNNI@)
|
|
set(GGML_AVX512_BF16 @GGML_AVX512_BF16@)
|
|
set(GGML_AMX_TILE @GGML_AMX_TILE@)
|
|
set(GGML_AMX_INT8 @GGML_AMX_INT8@)
|
|
set(GGML_AMX_BF16 @GGML_AMX_BF16@)
|
|
set(GGML_FMA @GGML_FMA@)
|
|
set(GGML_LASX @GGML_LASX@)
|
|
set(GGML_LSX @GGML_LSX@)
|
|
set(GGML_RVV @GGML_RVV@)
|
|
set(GGML_SVE @GGML_SVE@)
|
|
|
|
set(GGML_ACCELERATE @GGML_ACCELERATE@)
|
|
set(GGML_OPENMP @GGML_OPENMP@)
|
|
set(GGML_CPU_HBM @GGML_CPU_HBM@)
|
|
set(GGML_BLAS_VENDOR @GGML_BLAS_VENDOR@)
|
|
|
|
set(GGML_CUDA_FORCE_MMQ @GGML_CUDA_FORCE_MMQ@)
|
|
set(GGML_CUDA_FORCE_CUBLAS @GGML_CUDA_FORCE_CUBLAS@)
|
|
set(GGML_CUDA_F16 @GGML_CUDA_F16@)
|
|
set(GGML_CUDA_PEER_MAX_BATCH_SIZE @GGML_CUDA_PEER_MAX_BATCH_SIZE@)
|
|
set(GGML_CUDA_NO_PEER_COPY @GGML_CUDA_NO_PEER_COPY@)
|
|
set(GGML_CUDA_NO_VMM @GGML_CUDA_NO_VMM@)
|
|
set(GGML_CUDA_FA_ALL_QUANTS @GGML_CUDA_FA_ALL_QUANTS@)
|
|
set(GGML_CUDA_GRAPHS @GGML_CUDA_GRAPHS@)
|
|
|
|
set(GGML_HIP_UMA @GGML_HIP_UMA@)
|
|
|
|
set(GGML_VULKAN_CHECK_RESULTS @GGML_VULKAN_CHECK_RESULTS@)
|
|
set(GGML_VULKAN_DEBUG @GGML_VULKAN_DEBUG@)
|
|
set(GGML_VULKAN_MEMORY_DEBUG @GGML_VULKAN_MEMORY_DEBUG@)
|
|
set(GGML_VULKAN_SHADER_DEBUG_INFO @GGML_VULKAN_SHADER_DEBUG_INFO@)
|
|
set(GGML_VULKAN_PERF @GGML_VULKAN_PERF@)
|
|
set(GGML_VULKAN_VALIDATE @GGML_VULKAN_VALIDATE@)
|
|
set(GGML_VULKAN_RUN_TESTS @GGML_VULKAN_RUN_TESTS@)
|
|
|
|
set(GGML_METAL_USE_BF16 @GGML_METAL_USE_BF16@)
|
|
set(GGML_METAL_NDEBUG @GGML_METAL_NDEBUG@)
|
|
set(GGML_METAL_SHADER_DEBUG @GGML_METAL_SHADER_DEBUG@)
|
|
set(GGML_METAL_EMBED_LIBRARY @GGML_METAL_EMBED_LIBRARY@)
|
|
set(GGML_METAL_MACOSX_VERSION_MIN @GGML_METAL_MACOSX_VERSION_MIN@)
|
|
set(GGML_METAL_STD @GGML_METAL_STD@)
|
|
|
|
set(GGML_SYCL_F16 @GGML_SYCL_F16@)
|
|
set(GGML_SYCL_TARGET @GGML_SYCL_TARGET@)
|
|
set(GGML_SYCL_DEVICE_ARCH @GGML_SYCL_DEVICE_ARCH@)
|
|
|
|
|
|
@PACKAGE_INIT@
|
|
|
|
set_and_check(LLAMA_INCLUDE_DIR "@PACKAGE_LLAMA_INCLUDE_INSTALL_DIR@")
|
|
set_and_check(LLAMA_LIB_DIR "@PACKAGE_LLAMA_LIB_INSTALL_DIR@")
|
|
set_and_check(LLAMA_BIN_DIR "@PACKAGE_LLAMA_BIN_INSTALL_DIR@")
|
|
|
|
find_package(Threads REQUIRED)
|
|
|
|
set(_llama_transient_defines "@GGML_TRANSIENT_DEFINES@")
|
|
set(_llama_link_deps "")
|
|
set(_llama_link_opts "")
|
|
foreach(_ggml_lib ggml ggml-base)
|
|
string(REPLACE "-" "_" _ggml_lib_var "${_ggml_lib}_LIBRARY")
|
|
find_library(${_ggml_lib_var} ${_ggml_lib}
|
|
REQUIRED
|
|
HINTS ${LLAMA_LIB_DIR}
|
|
NO_CMAKE_FIND_ROOT_PATH
|
|
)
|
|
list(APPEND _llama_link_deps "${${_ggml_lib_var}}")
|
|
message(STATUS "Found ${${_ggml_lib_var}}")
|
|
endforeach()
|
|
|
|
foreach(backend amx blas cann cpu cuda hip kompute metal musa rpc sycl vulkan)
|
|
string(TOUPPER "GGML_${backend}" backend_id)
|
|
set(_ggml_lib "ggml-${backend}")
|
|
string(REPLACE "-" "_" _ggml_lib_var "${_ggml_lib}_LIBRARY")
|
|
|
|
find_library(${_ggml_lib_var} ${_ggml_lib}
|
|
HINTS ${LLAMA_LIB_DIR}
|
|
NO_CMAKE_FIND_ROOT_PATH
|
|
)
|
|
if(${_ggml_lib_var})
|
|
list(APPEND _llama_link_deps "${${_ggml_lib_var}}")
|
|
set(${backend_id} ON)
|
|
message(STATUS "Found backend ${${_ggml_lib_var}}")
|
|
else()
|
|
set(${backend_id} OFF)
|
|
endif()
|
|
endforeach()
|
|
|
|
if (NOT LLAMA_SHARED_LIB)
|
|
if (APPLE AND GGML_ACCELERATE)
|
|
find_library(ACCELERATE_FRAMEWORK Accelerate REQUIRED)
|
|
list(APPEND _llama_link_deps ${ACCELERATE_FRAMEWORK})
|
|
endif()
|
|
|
|
if (GGML_OPENMP)
|
|
find_package(OpenMP REQUIRED)
|
|
list(APPEND _llama_link_deps OpenMP::OpenMP_C OpenMP::OpenMP_CXX)
|
|
endif()
|
|
|
|
if (GGML_CPU_HBM)
|
|
find_library(memkind memkind REQUIRED)
|
|
list(APPEND _llama_link_deps memkind)
|
|
endif()
|
|
|
|
if (GGML_BLAS)
|
|
find_package(BLAS REQUIRED)
|
|
list(APPEND _llama_link_deps ${BLAS_LIBRARIES})
|
|
list(APPEND _llama_link_opts ${BLAS_LINKER_FLAGS})
|
|
endif()
|
|
|
|
if (GGML_CUDA)
|
|
find_package(CUDAToolkit REQUIRED)
|
|
endif()
|
|
|
|
if (GGML_METAL)
|
|
find_library(FOUNDATION_LIBRARY Foundation REQUIRED)
|
|
find_library(METAL_FRAMEWORK Metal REQUIRED)
|
|
find_library(METALKIT_FRAMEWORK MetalKit REQUIRED)
|
|
list(APPEND _llama_link_deps ${FOUNDATION_LIBRARY}
|
|
${METAL_FRAMEWORK} ${METALKIT_FRAMEWORK})
|
|
endif()
|
|
|
|
if (GGML_VULKAN)
|
|
find_package(Vulkan REQUIRED)
|
|
list(APPEND _llama_link_deps Vulkan::Vulkan)
|
|
endif()
|
|
|
|
if (GGML_HIP)
|
|
find_package(hip REQUIRED)
|
|
find_package(hipblas REQUIRED)
|
|
find_package(rocblas REQUIRED)
|
|
list(APPEND _llama_link_deps hip::host roc::rocblas roc::hipblas)
|
|
endif()
|
|
|
|
if (GGML_SYCL)
|
|
find_package(DNNL)
|
|
if (${DNNL_FOUND} AND GGML_SYCL_TARGET STREQUAL "INTEL")
|
|
list(APPEND _llama_link_deps DNNL::dnnl)
|
|
endif()
|
|
if (WIN32)
|
|
find_package(IntelSYCL REQUIRED)
|
|
find_package(MKL REQUIRED)
|
|
list(APPEND _llama_link_deps IntelSYCL::SYCL_CXX MKL::MKL MKL::MKL_SYCL)
|
|
endif()
|
|
endif()
|
|
endif()
|
|
|
|
find_library(llama_LIBRARY llama
|
|
REQUIRED
|
|
HINTS ${LLAMA_LIB_DIR}
|
|
NO_CMAKE_FIND_ROOT_PATH
|
|
)
|
|
|
|
add_library(llama UNKNOWN IMPORTED)
|
|
set_target_properties(llama
|
|
PROPERTIES
|
|
INTERFACE_INCLUDE_DIRECTORIES "${LLAMA_INCLUDE_DIR}"
|
|
INTERFACE_LINK_LIBRARIES "${_llama_link_deps}"
|
|
INTERFACE_LINK_OPTIONS "${_llama_link_opts}"
|
|
INTERFACE_COMPILE_DEFINITIONS "${_llama_transient_defines}"
|
|
IMPORTED_LINK_INTERFACE_LANGUAGES "CXX"
|
|
IMPORTED_LOCATION "${llama_LIBRARY}"
|
|
INTERFACE_COMPILE_FEATURES cxx_std_11
|
|
POSITION_INDEPENDENT_CODE ON )
|
|
|
|
check_required_components(Llama)
|