Files
llama.cpp/ggml/src/ggml-metal/CMakeLists.txt
Georgi Gerganov 0320ac5264 metal : refactor + optimize v2 (#15995)
* metal : improve naming

* metal : refactor device

ggml-ci

* cont : props

ggml-ci

* metal : apply ggml_mem_ranges_t

ggml-ci

* metal : remove GGML_METAL_USE_BF16

ggml-ci

* metal : refactor device buffer

ggml-ci

* cont : fix naming

* metal : sync before destroying the backend

ggml-ci

* metal : refactor context

ggml-ci

* metal : migrate ggml-metal.m to ggml-metal.cpp

ggml-ci

* metal : adjust ops API

ggml-ci

* metal : use C++ to store piplienes

ggml-ci

* metal : migrate ops to separate functions

ggml-ci

* metal : add ggml_metal_library_t

ggml-ci

* metal : improve naming

ggml-ci

* metal : cleanp

ggml-ci

* metal : add support for GGML_OP_LOG

ggml-ci

* metal : fix error handling

ggml-ci
2025-09-17 20:38:12 +03:00

125 lines
5.6 KiB
CMake

find_library(FOUNDATION_LIBRARY Foundation REQUIRED)
find_library(METAL_FRAMEWORK Metal REQUIRED)
find_library(METALKIT_FRAMEWORK MetalKit REQUIRED)
message(STATUS "Metal framework found")
ggml_add_backend_library(ggml-metal
ggml-metal.cpp
ggml-metal-device.m
ggml-metal-device.cpp
ggml-metal-common.cpp
ggml-metal-context.m
ggml-metal-ops.cpp
)
target_link_libraries(ggml-metal PRIVATE
${FOUNDATION_LIBRARY}
${METAL_FRAMEWORK}
${METALKIT_FRAMEWORK}
)
if (GGML_METAL_NDEBUG)
add_compile_definitions(GGML_METAL_NDEBUG)
endif()
# copy metal files to bin directory
configure_file(../ggml-common.h ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-common.h COPYONLY)
configure_file(ggml-metal.metal ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal COPYONLY)
configure_file(ggml-metal-impl.h ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal-impl.h COPYONLY)
set(METALLIB_COMMON "${CMAKE_CURRENT_SOURCE_DIR}/../ggml-common.h")
if (GGML_METAL_EMBED_LIBRARY)
enable_language(ASM)
add_compile_definitions(GGML_METAL_EMBED_LIBRARY)
set(METALLIB_SOURCE "${CMAKE_CURRENT_SOURCE_DIR}/ggml-metal.metal")
set(METALLIB_IMPL "${CMAKE_CURRENT_SOURCE_DIR}/ggml-metal-impl.h")
file(MAKE_DIRECTORY "${CMAKE_BINARY_DIR}/autogenerated")
# merge ggml-common.h and ggml-metal.metal into a single file
set(METALLIB_EMBED_ASM "${CMAKE_BINARY_DIR}/autogenerated/ggml-metal-embed.s")
set(METALLIB_SOURCE_EMBED "${CMAKE_BINARY_DIR}/autogenerated/ggml-metal-embed.metal")
set(METALLIB_SOURCE_EMBED_TMP "${CMAKE_BINARY_DIR}/autogenerated/ggml-metal-embed.metal.tmp")
add_custom_command(
OUTPUT "${METALLIB_EMBED_ASM}"
COMMAND echo "Embedding Metal library"
COMMAND sed -e "/__embed_ggml-common.h__/r ${METALLIB_COMMON}" -e "/__embed_ggml-common.h__/d" < "${METALLIB_SOURCE}" > "${METALLIB_SOURCE_EMBED_TMP}"
COMMAND sed -e "/\#include \"ggml-metal-impl.h\"/r ${METALLIB_IMPL}" -e "/\#include \"ggml-metal-impl.h\"/d" < "${METALLIB_SOURCE_EMBED_TMP}" > "${METALLIB_SOURCE_EMBED}"
COMMAND echo ".section __DATA,__ggml_metallib" > "${METALLIB_EMBED_ASM}"
COMMAND echo ".globl _ggml_metallib_start" >> "${METALLIB_EMBED_ASM}"
COMMAND echo "_ggml_metallib_start:" >> "${METALLIB_EMBED_ASM}"
COMMAND echo .incbin "\"${METALLIB_SOURCE_EMBED}\"" >> "${METALLIB_EMBED_ASM}"
COMMAND echo ".globl _ggml_metallib_end" >> "${METALLIB_EMBED_ASM}"
COMMAND echo "_ggml_metallib_end:" >> "${METALLIB_EMBED_ASM}"
DEPENDS ../ggml-common.h ggml-metal.metal ggml-metal-impl.h
COMMENT "Generate assembly for embedded Metal library"
VERBATIM
)
target_sources(ggml-metal PRIVATE "${METALLIB_EMBED_ASM}")
else()
if (GGML_METAL_SHADER_DEBUG)
# custom command to do the following:
# xcrun -sdk macosx metal -fno-fast-math -c ggml-metal.metal -o ggml-metal.air
# xcrun -sdk macosx metallib ggml-metal.air -o default.metallib
#
# note: this is the only way I found to disable fast-math in Metal. it's ugly, but at least it works
# disabling fast math is needed in order to pass tests/test-backend-ops
# note: adding -fno-inline fixes the tests when using MTL_SHADER_VALIDATION=1
# note: unfortunately, we have to call it default.metallib instead of ggml.metallib
# ref: https://github.com/ggerganov/whisper.cpp/issues/1720
# note: adding -g causes segmentation fault during compile
#set(XC_FLAGS -fno-fast-math -fno-inline -g)
set(XC_FLAGS -fno-fast-math -fno-inline)
else()
set(XC_FLAGS -O3)
endif()
# Append macOS metal versioning flags
if (GGML_METAL_MACOSX_VERSION_MIN)
message(STATUS "Adding -mmacosx-version-min=${GGML_METAL_MACOSX_VERSION_MIN} flag to metal compilation")
list (APPEND XC_FLAGS -mmacosx-version-min=${GGML_METAL_MACOSX_VERSION_MIN})
endif()
if (GGML_METAL_STD)
message(STATUS "Adding -std=${GGML_METAL_STD} flag to metal compilation")
list (APPEND XC_FLAGS -std=${GGML_METAL_STD})
endif()
add_custom_command(
OUTPUT ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
COMMAND xcrun -sdk macosx metal ${XC_FLAGS} -c ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal -o - |
xcrun -sdk macosx metallib - -o ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
COMMAND rm -f ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-common.h
COMMAND rm -f ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal
DEPENDS ggml-metal.metal ${METALLIB_COMMON}
COMMENT "Compiling Metal kernels"
)
# FIXME: only add to the ggml-metal target?
add_custom_target(
ggml-metal-lib ALL
DEPENDS ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
)
endif() # GGML_METAL_EMBED_LIBRARY
if (NOT GGML_METAL_EMBED_LIBRARY)
install(
FILES src/ggml-metal/ggml-metal.metal
PERMISSIONS
OWNER_READ
OWNER_WRITE
GROUP_READ
WORLD_READ
DESTINATION ${CMAKE_INSTALL_BINDIR})
install(
FILES ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
DESTINATION ${CMAKE_INSTALL_BINDIR}
)
endif()