ollama/CMakeLists.txt
Michael Yang dcfb7a105c
next build (#8539)
* add build to .dockerignore

* test: only build one arch

* add build to .gitignore

* fix ccache path

* filter amdgpu targets

* only filter if autodetecting

* Don't clobber gpu list for default runner

This ensures the GPU specific environment variables are set properly

* explicitly set CXX compiler for HIP

* Update build_windows.ps1

This isn't complete, but is close.  Dependencies are missing, and it only builds the "default" preset.

* build: add ollama subdir

* add .git to .dockerignore

* docs: update development.md

* update build_darwin.sh

* remove unused scripts

* llm: add cwd and build/lib/ollama to library paths

* default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS

* add additional cmake output vars for msvc

* interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12

* remove unncessary filepath.Dir, cleanup

* add hardware-specific directory to path

* use absolute server path

* build: linux arm

* cmake install targets

* remove unused files

* ml: visit each library path once

* build: skip cpu variants on arm

* build: install cpu targets

* build: fix workflow

* shorter names

* fix rocblas install

* docs: clean up development.md

* consistent build dir removal in development.md

* silence -Wimplicit-function-declaration build warnings in ggml-cpu

* update readme

* update development readme

* llm: update library lookup logic now that there is one runner (#8587)

* tweak development.md

* update docs

* add windows cuda/rocm tests

---------

Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2025-01-29 15:03:38 -08:00

113 lines
4.0 KiB
CMake

cmake_minimum_required(VERSION 3.21)
project(Ollama C CXX)
include(CheckLanguage)
find_package(Threads REQUIRED)
set(CMAKE_BUILD_TYPE Release)
set(BUILD_SHARED_LIBS ON)
set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_CXX_EXTENSIONS OFF)
set(GGML_BUILD ON)
set(GGML_SHARED ON)
set(GGML_CCACHE ON)
set(GGML_BACKEND_DL ON)
set(GGML_BACKEND_SHARED ON)
set(GGML_SCHED_MAX_COPIES 4)
set(GGML_LLAMAFILE ON)
set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128)
set(GGML_CUDA_GRAPHS ON)
if((NOT CMAKE_OSX_ARCHITECTURES MATCHES "arm64")
OR (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm|aarch64|ARM64|ARMv[0-9]+"))
set(GGML_CPU_ALL_VARIANTS ON)
endif()
set(OLLAMA_BUILD_DIR ${CMAKE_BINARY_DIR}/lib/ollama)
set(OLLAMA_INSTALL_DIR ${CMAKE_INSTALL_PREFIX}/lib/ollama)
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${OLLAMA_BUILD_DIR})
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY_DEBUG ${OLLAMA_BUILD_DIR})
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY_RELEASE ${OLLAMA_BUILD_DIR})
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${OLLAMA_BUILD_DIR})
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY_DEBUG ${OLLAMA_BUILD_DIR})
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY_RELEASE ${OLLAMA_BUILD_DIR})
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src)
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/include)
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-cpu)
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-cpu/amx)
set(GGML_CPU ON)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src)
set_property(TARGET ggml PROPERTY EXCLUDE_FROM_ALL TRUE)
get_target_property(CPU_VARIANTS ggml-cpu MANUALLY_ADDED_DEPENDENCIES)
if(NOT CPU_VARIANTS)
set(CPU_VARIANTS "ggml-cpu")
endif()
install(TARGETS ggml-base ${CPU_VARIANTS}
RUNTIME_DEPENDENCIES
PRE_EXCLUDE_REGEXES ".*"
RUNTIME DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CPU
LIBRARY DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CPU
FRAMEWORK DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CPU
)
check_language(CUDA)
if(CMAKE_CUDA_COMPILER)
if(CMAKE_VERSION VERSION_GREATER_EQUAL "3.24" AND NOT CMAKE_CUDA_ARCHITECTURES)
set(CMAKE_CUDA_ARCHITECTURES "native")
endif()
find_package(CUDAToolkit)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-cuda)
set(OLLAMA_CUDA_INSTALL_DIR ${OLLAMA_INSTALL_DIR}/cuda_v${CUDAToolkit_VERSION_MAJOR})
install(TARGETS ggml-cuda
RUNTIME_DEPENDENCIES
DIRECTORIES ${CUDAToolkit_BIN_DIR} ${CUDAToolkit_LIBRARY_DIR}
PRE_INCLUDE_REGEXES cublas cublasLt cudart
PRE_EXCLUDE_REGEXES ".*"
RUNTIME DESTINATION ${OLLAMA_CUDA_INSTALL_DIR} COMPONENT CUDA
LIBRARY DESTINATION ${OLLAMA_CUDA_INSTALL_DIR} COMPONENT CUDA
)
endif()
check_language(HIP)
if(CMAKE_HIP_COMPILER)
set(HIP_PLATFORM "amd")
find_package(hip REQUIRED)
if(NOT AMDGPU_TARGETS)
list(FILTER AMDGPU_TARGETS INCLUDE REGEX "^gfx(900|94[012]|101[02]|1030|110[012])$")
endif()
if(AMDGPU_TARGETS)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-hip)
set(OLLAMA_HIP_INSTALL_DIR ${OLLAMA_INSTALL_DIR}/rocm)
install(TARGETS ggml-hip
RUNTIME_DEPENDENCIES
DIRECTORIES ${HIP_BIN_INSTALL_DIR} ${HIP_LIB_INSTALL_DIR}
PRE_INCLUDE_REGEXES amdhip64 hipblas rocblas amd_comgr hsa_runtime64 rocprofiler-register drm_amdgpu drm numa
PRE_EXCLUDE_REGEXES ".*"
POST_EXCLUDE_REGEXES "system32"
RUNTIME DESTINATION ${OLLAMA_HIP_INSTALL_DIR} COMPONENT HIP
LIBRARY DESTINATION ${OLLAMA_HIP_INSTALL_DIR} COMPONENT HIP
)
foreach(HIP_LIB_BIN_INSTALL_DIR IN ITEMS ${HIP_BIN_INSTALL_DIR} ${HIP_LIB_INSTALL_DIR})
if(EXISTS ${HIP_LIB_BIN_INSTALL_DIR}/rocblas)
install(DIRECTORY ${HIP_LIB_BIN_INSTALL_DIR}/rocblas DESTINATION ${OLLAMA_HIP_INSTALL_DIR} COMPONENT HIP)
break()
endif()
endforeach()
endif()
endif()