metal: per-op source split + parallel compile (#26561)

* metal : per-op source split + parallel compile (#24021)

* preliminary extract common header

* op source split

* split metallib into 8 libs && load in parallel

* derive kernel->library routing from functionNames

* x-macro lib list + underscore filenames, dedup QK_NL, MRC fixes

* op source split 8 to 20

* improve robustness of source fallback

* clean up

* change bool -> atomic_bool

* only prepend headers that source actually includes

* no semaphore, use GCD global queue

* dedup library compile path, fix NSError lifetime, rename gla

* relocate upstream concat/rope_back/repeat kernel changes into split files

* move ggml-common.h from common.h into dequantize.h to shrink binary size

---------

Co-authored-by: lvyichen <lvyichen@stepfun.com>

* metal: add col2im_1d op (f32/f16/bf16) (#25176)

* metal : add set_rows with src0 f16 (#25434)

* metal : add CONV_2D_DW (depthwise convolution) support (#21565)

* metal : add Q2_0 support (#25419)

* metal: fuse snake activation (mul, sin, sqr, mul, add) (#25459)

* ggml-metal: FWHT kernel for metal backend (#25924)

* metal : port new kernels into the split sources

Move the kernels added on master after the split (lightning indexer,
DSv4 hyper-connections, silu_back, f16 bin ops, TQ2_0, the flash-attn KV
dequantization pass, rope offset/inplace, ssm_scan rollback, packed q8_0
dequantization and the tensor-API mat-mat K clamp) into the corresponding
kernels/*.metal sources. Copied verbatim, no functional change.

---------

Co-authored-by: lvyichen <lvyichen@stepfun.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
YiChen Lv
2026-08-24 19:16:13 +03:00
committed by GitHub
co-authored by lvyichen Georgi Gerganov
parent b3c3b96a13
commit b615f5b4bd
27 changed files with 12461 additions and 12069 deletions
+119 -51
View File
@@ -24,62 +24,119 @@ if (GGML_METAL_NDEBUG)
endif()
set(METALLIB_COMMON "${CMAKE_CURRENT_SOURCE_DIR}/../ggml-common.h")
set(METALLIB_KERNELS_COMMON "${CMAKE_CURRENT_SOURCE_DIR}/kernels/common.h")
set(METALLIB_KERNELS_DEQUANTIZE "${CMAKE_CURRENT_SOURCE_DIR}/kernels/dequantize.h")
set(METALLIB_KERNELS_QUANTIZE "${CMAKE_CURRENT_SOURCE_DIR}/kernels/quantize.h")
set(METALLIB_KERNEL_SOURCES
kernels/fa.metal
kernels/mul_mv.metal
kernels/mul_mm.metal
kernels/quantize.metal
kernels/softmax.metal
kernels/norm.metal
kernels/unary.metal
kernels/binbcast.metal
kernels/reduce.metal
kernels/tri.metal
kernels/ssm.metal
kernels/wkv.metal
kernels/gated_delta_net.metal
kernels/solve_tri.metal
kernels/rope.metal
kernels/conv.metal
kernels/upscale.metal
kernels/argsort.metal
kernels/pool.metal
kernels/misc.metal
)
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")
set(METALLIB_IMPL "${CMAKE_CURRENT_SOURCE_DIR}/ggml-metal-impl.h")
file(MAKE_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}/autogenerated")
# merge ggml-common.h and ggml-metal.metal into a single file
set(METALLIB_EMBED_ASM "${CMAKE_CURRENT_BINARY_DIR}/autogenerated/ggml-metal-embed.s")
set(METALLIB_SOURCE_EMBED "${CMAKE_CURRENT_BINARY_DIR}/autogenerated/ggml-metal-embed.metal")
set(METALLIB_SOURCE_EMBED_TMP "${CMAKE_CURRENT_BINARY_DIR}/autogenerated/ggml-metal-embed.metal.tmp")
set(METALLIB_EMBED_ASM_FILES "")
foreach(src ${METALLIB_KERNEL_SOURCES})
get_filename_component(kind ${src} NAME_WE)
# symbol names must be valid C identifiers ('-' is not allowed)
string(REPLACE "-" "_" kind_sym ${kind})
add_custom_command(
OUTPUT "${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
)
set(SRC "${CMAKE_CURRENT_SOURCE_DIR}/kernels/${kind}.metal")
set(EMBED "${CMAKE_CURRENT_BINARY_DIR}/autogenerated/ggml-metal-embed-${kind}.metal")
set(ASM "${CMAKE_CURRENT_BINARY_DIR}/autogenerated/ggml-metal-embed-${kind}.s")
target_sources(ggml-metal PRIVATE "${METALLIB_EMBED_ASM}")
# only prepend headers that this source actually includes
set(HEADERS_FOR_SRC ${METALLIB_KERNELS_COMMON})
file(STRINGS ${SRC} _has_dequantize REGEX "#include \"dequantize\\.h\"")
file(STRINGS ${SRC} _has_quantize REGEX "#include \"quantize\\.h\"")
if(_has_dequantize)
list(APPEND HEADERS_FOR_SRC ${METALLIB_KERNELS_DEQUANTIZE})
endif()
if(_has_quantize)
list(APPEND HEADERS_FOR_SRC ${METALLIB_KERNELS_QUANTIZE})
endif()
add_custom_command(
OUTPUT "${ASM}"
# Step 1: concatenate shared headers + this kernel source
COMMAND cat ${HEADERS_FOR_SRC} ${SRC} > "${EMBED}.tmp1"
# Step 2: remove internal #include and #pragma once
COMMAND sed -e "/\#include \"common.h\"/d" -e "/\#include \"dequantize.h\"/d" -e "/\#include \"quantize.h\"/d" -e "/\#pragma once/d" < "${EMBED}.tmp1" > "${EMBED}.tmp2"
# Step 3: inline ggml-common.h (replacing __embed_ggml-common.h__ sentinel)
COMMAND sed -e "/__embed_ggml-common.h__/r ${METALLIB_COMMON}" -e "/__embed_ggml-common.h__/d" < "${EMBED}.tmp2" > "${EMBED}.tmp3"
# Step 4: inline ggml-metal-impl.h
COMMAND sed -e "/\#include \"ggml-metal-impl.h\"/r ${METALLIB_IMPL}" -e "/\#include \"ggml-metal-impl.h\"/d" < "${EMBED}.tmp3" > "${EMBED}"
# Step 5: emit an asm chunk with kind-specific start/end symbols
# note: '-' is illegal in C symbols, so we use kind_sym; the macOS
# section name is limited to 16 chars so we keep it shared
# across kinds (__ggml_metallib) and only vary the global symbols.
COMMAND echo ".section __DATA,__ggml_metallib" > "${ASM}"
COMMAND echo ".globl _ggml_metallib_${kind_sym}_start" >> "${ASM}"
COMMAND echo "_ggml_metallib_${kind_sym}_start:" >> "${ASM}"
COMMAND echo .incbin "\"${EMBED}\"" >> "${ASM}"
COMMAND echo ".globl _ggml_metallib_${kind_sym}_end" >> "${ASM}"
COMMAND echo "_ggml_metallib_${kind_sym}_end:" >> "${ASM}"
DEPENDS ../ggml-common.h ggml-metal-impl.h
kernels/common.h kernels/dequantize.h kernels/quantize.h
kernels/${kind}.metal
COMMENT "Generate embedded Metal library for ${kind}"
VERBATIM
)
list(APPEND METALLIB_EMBED_ASM_FILES "${ASM}")
endforeach()
target_sources(ggml-metal PRIVATE ${METALLIB_EMBED_ASM_FILES})
else()
# copy metal files to bin directory
# copy header 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 ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal-impl.h COPYONLY)
file(MAKE_DIRECTORY "${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/kernels")
configure_file(kernels/common.h ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/kernels/common.h COPYONLY)
configure_file(kernels/dequantize.h ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/kernels/dequantize.h COPYONLY)
configure_file(kernels/quantize.h ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/kernels/quantize.h COPYONLY)
foreach(src ${METALLIB_KERNEL_SOURCES})
configure_file(${src} ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/${src} COPYONLY)
endforeach()
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: 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/ggml-org/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})
@@ -90,35 +147,46 @@ else()
list (APPEND XC_FLAGS -std=${GGML_METAL_STD})
endif()
# Compile each kernel source to .air, then link into default.metallib
set(AIR_FILES "")
foreach(src ${METALLIB_KERNEL_SOURCES})
get_filename_component(name ${src} NAME_WE)
set(AIR "${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/${name}.air")
list(APPEND AIR_FILES ${AIR})
add_custom_command(
OUTPUT ${AIR}
COMMAND xcrun -sdk macosx metal ${XC_FLAGS} -I ${CMAKE_RUNTIME_OUTPUT_DIRECTORY} -c ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/${src} -o ${AIR}
DEPENDS ${src} kernels/common.h kernels/dequantize.h kernels/quantize.h ${METALLIB_COMMON} ggml-metal-impl.h
COMMENT "Compiling ${src}"
VERBATIM
)
endforeach()
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 xcrun -sdk macosx metallib ${AIR_FILES} -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"
)
COMMAND rm -f ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal-impl.h
COMMAND rm -rf ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/kernels
DEPENDS ${AIR_FILES}
COMMENT "Linking Metal kernels into default.metallib"
)
# 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})
DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/kernels/
DESTINATION ${CMAKE_INSTALL_BINDIR}/kernels
FILES_MATCHING PATTERN "*.metal" PATTERN "*.h"
)
install(
FILES ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
DESTINATION ${CMAKE_INSTALL_BINDIR}
)
install(
FILES ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
DESTINATION ${CMAKE_INSTALL_BINDIR}
)
endif()