ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : Metal inference (#1642)

Browse source 
* mtl : export the LLaMA computation graph

* ci : disable temporary

* mtl : adapt the MNIST example as starter

* mtl : no need for mtl-export tool, add cli arg for main instead

* mtl : export just a small part of the graph for now to make it easier

* mtl : move MSL code into separate file for easy editing

* mtl : initial get_rows_q4_0 kernel

* mtl : confirmed get_rows_q4_0 is working correctly

* mtl : add rms_norm kernel + confirm working

* mtl : add mul kernel + confirm working

* mtl : initial mul_mat Q4 kernel (wrong results)

* mtl : mul_mat fixes (still wrong)

* mtl : another mul_mat Q4 (still does not work)

* mtl : working mul_mat q4

* ggml : fix handling of "view" ops in ggml_graph_import()

* mtl : add rope kernel

* mtl : add reshape and transpose handling

* ggml : store offset as opt arg for ggml_view_xd() operators

* mtl : add cpy kernel + handle view ops

* mtl : confirm f16 x f32 attention mul mat

* mtl : add scale kernel

* mtl : add diag_mask_inf kernel

* mtl : fix soft_max kernel

* ggml : update ggml_nbytes() to handle non-contiguous tensors

* mtl : verify V tensor contents

* mtl : add f32 -> f32 cpy kernel

* mtl : add silu kernel

* mtl : add non-broadcast mul kernel

* mtl : full GPU inference of the computation graph

* mtl : optimize rms_norm and soft_max kernels

* mtl : add f16 mat x f32 vec multiplication kernel

* mtl : fix bug in f16 x f32 mul mat + speed-up computation

* mtl : faster mul_mat_q4_0_f32 kernel

* mtl : fix kernel signature + roll inner loop

* mtl : more threads for rms_norm + better timing

* mtl : remove printfs from inner loop

* mtl : simplify implementation

* mtl : add save/load vocab to ggml file

* mtl : plug Metal inference into llama.cpp (very quick-n-dirty)

* mtl : make it work with main example

Lots of hacks but at least now it generates text

* mtl : preparing for merge

* mtl : clean-up ggml mtl interface + suport scratch / inplace

* mtl : remove temp / debug code

* metal : final refactoring and simplification

* Revert "ci : disable temporary"

This reverts commit 98c267fc77fe811082f672538fc91bcfc9072d63.

* metal : add comments

* metal : clean-up stuff, fix typos

* readme : add Metal instructions

* readme : add example for main
This commit is contained in:
Georgi Gerganov 2023-06-04 23:34:30 +03:00 • committed by GitHub
parent dcb2ed4826
commit ecb217db4f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
17 changed files with 1677 additions and 94 deletions
Download patch file Download diff file Expand all files Collapse all files

62
CMakeLists.txt
View file

@ -64,13 +64,14 @@ if (NOT MSVC)
endif()
# 3rd party libs
option(LLAMA_ACCELERATE "llama: enable Accelerate framework" ON)
option(LLAMA_BLAS "llama: use BLAS" OFF)
option(LLAMA_ACCELERATE "llama: enable Accelerate framework" ON)
option(LLAMA_BLAS "llama: use BLAS" OFF)
set(LLAMA_BLAS_VENDOR "Generic" CACHE STRING "llama: BLAS library vendor")
option(LLAMA_CUBLAS "llama: use cuBLAS" OFF)
set(LLAMA_CUDA_DMMV_X "32" CACHE STRING "llama: x stride for dmmv CUDA kernels")
set(LLAMA_CUDA_DMMV_Y "1" CACHE STRING "llama: y block size for dmmv CUDA kernels")
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
option(LLAMA_CUBLAS "llama: use cuBLAS" OFF)
set(LLAMA_CUDA_DMMV_X "32" CACHE STRING "llama: x stride for dmmv CUDA kernels")
set(LLAMA_CUDA_DMMV_Y "1" CACHE STRING "llama: y block size for dmmv CUDA kernels")
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
option(LLAMA_METAL "llama: use Metal" OFF)
option(LLAMA_BUILD_TESTS "llama: build tests" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE})
@ -183,7 +184,7 @@ if (LLAMA_CUBLAS)
enable_language(CUDA)
set(GGML_CUDA_SOURCES ggml-cuda.cu ggml-cuda.h)
set(GGML_SOURCES_CUDA ggml-cuda.cu ggml-cuda.h)
add_compile_definitions(GGML_USE_CUBLAS)
add_compile_definitions(GGML_CUDA_DMMV_X=${LLAMA_CUDA_DMMV_X})
@ -200,12 +201,37 @@ if (LLAMA_CUBLAS)
endif()
endif()
if (LLAMA_METAL)
find_library(FOUNDATION_LIBRARY Foundation REQUIRED)
find_library(METAL_FRAMEWORK Metal REQUIRED)
find_library(METALKIT_FRAMEWORK MetalKit REQUIRED)
find_library(METALPERFORMANCE_FRAMEWORK MetalPerformanceShaders REQUIRED)
set(GGML_SOURCES_METAL ggml-metal.m ggml-metal.h)
add_compile_definitions(GGML_USE_METAL)
add_compile_definitions(GGML_METAL_NDEBUG)
# get full path to the file
#add_compile_definitions(GGML_METAL_DIR_KERNELS="${CMAKE_CURRENT_SOURCE_DIR}/")
# copy ggml-metal.metal to bin directory
configure_file(ggml-metal.metal bin/ggml-metal.metal COPYONLY)
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS}
${FOUNDATION_LIBRARY}
${METAL_FRAMEWORK}
${METALKIT_FRAMEWORK}
${METALPERFORMANCE_FRAMEWORK}
)
endif()
if (LLAMA_CLBLAST)
find_package(CLBlast)
if (CLBlast_FOUND)
message(STATUS "CLBlast found")
set(GGML_OPENCL_SOURCES ggml-opencl.cpp ggml-opencl.h)
set(GGML_SOURCES_OPENCL ggml-opencl.cpp ggml-opencl.h)
add_compile_definitions(GGML_USE_CLBLAST)
@ -370,8 +396,10 @@ endif()
add_library(ggml OBJECT
ggml.c
ggml.h
${GGML_CUDA_SOURCES}
${GGML_OPENCL_SOURCES})
${GGML_SOURCES_CUDA}
${GGML_SOURCES_OPENCL}
${GGML_SOURCES_METAL}
)
target_include_directories(ggml PUBLIC .)
target_compile_features(ggml PUBLIC c_std_11) # don't bump
@ -384,21 +412,25 @@ endif()
add_library(llama
llama.cpp
llama.h
llama-util.h)
llama-util.h
)
target_include_directories(llama PUBLIC .)
target_compile_features(llama PUBLIC cxx_std_11) # don't bump
target_link_libraries(llama PRIVATE ggml ${LLAMA_EXTRA_LIBS})
target_link_libraries(llama PRIVATE
ggml
${LLAMA_EXTRA_LIBS}
)
if (BUILD_SHARED_LIBS)
set_target_properties(llama PROPERTIES POSITION_INDEPENDENT_CODE ON)
target_compile_definitions(llama PRIVATE LLAMA_SHARED LLAMA_BUILD)
endif()
if (GGML_CUDA_SOURCES)
if (GGML_SOURCES_CUDA)
message(STATUS "GGML CUDA sources found, configuring CUDA architecture")
set_property(TARGET ggml PROPERTY CUDA_ARCHITECTURES OFF)
set_property(TARGET ggml PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
set_property(TARGET ggml PROPERTY CUDA_ARCHITECTURES OFF)
set_property(TARGET ggml PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
set_property(TARGET llama PROPERTY CUDA_ARCHITECTURES OFF)
endif()