Merge 'origin/master' into hipblas
This commit is contained in:
Henri Vasserman
commit
33091a9bd3
37 changed files with 5867 additions and 253 deletions
|
|
@ -3,7 +3,7 @@ ARG UBUNTU_VERSION=22.04
|
|||
FROM ubuntu:$UBUNTU_VERSION as build
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential python3 python3-pip
|
||||
apt-get install -y build-essential python3 python3-pip git
|
||||
|
||||
COPY requirements.txt requirements.txt
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ ARG UBUNTU_VERSION=22.04
|
|||
FROM ubuntu:$UBUNTU_VERSION as build
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y build-essential
|
||||
apt-get install -y build-essential git
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ shift
|
|||
arg2="$@"
|
||||
|
||||
if [[ $arg1 == '--convert' || $arg1 == '-c' ]]; then
|
||||
python3 ./convert-pth-to-ggml.py $arg2
|
||||
python3 ./convert.py $arg2
|
||||
elif [[ $arg1 == '--quantize' || $arg1 == '-q' ]]; then
|
||||
./quantize $arg2
|
||||
elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then
|
||||
|
|
@ -32,7 +32,7 @@ else
|
|||
echo " --run (-r): Run a model previously converted into ggml"
|
||||
echo " ex: -m /models/7B/ggml-model-q4_0.bin -p \"Building a website can be done in 10 simple steps:\" -n 512"
|
||||
echo " --convert (-c): Convert a llama model into ggml"
|
||||
echo " ex: \"/models/7B/\" 1"
|
||||
echo " ex: --outtype f16 \"/models/7B/\" "
|
||||
echo " --quantize (-q): Optimize with quantization process ggml"
|
||||
echo " ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
|
||||
echo " --all-in-one (-a): Execute --convert & --quantize"
|
||||
|
|
|
|||
16
.github/workflows/build.yml
vendored
16
.github/workflows/build.yml
vendored
|
|
@ -10,10 +10,10 @@ on:
|
|||
push:
|
||||
branches:
|
||||
- master
|
||||
paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
|
||||
paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp']
|
||||
pull_request:
|
||||
types: [opened, synchronize, reopened]
|
||||
paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
|
||||
paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp']
|
||||
|
||||
env:
|
||||
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
|
||||
|
|
@ -157,15 +157,15 @@ jobs:
|
|||
matrix:
|
||||
include:
|
||||
- build: 'avx2'
|
||||
defines: ''
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON'
|
||||
- build: 'avx'
|
||||
defines: '-DLLAMA_AVX2=OFF'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF'
|
||||
- build: 'avx512'
|
||||
defines: '-DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
|
||||
- build: 'clblast'
|
||||
defines: '-DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
|
||||
- build: 'openblas'
|
||||
defines: '-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
|
|
@ -292,7 +292,7 @@ jobs:
|
|||
run: |
|
||||
mkdir build
|
||||
cd build
|
||||
cmake .. -DLLAMA_CUBLAS=ON
|
||||
cmake .. -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON
|
||||
cmake --build . --config Release
|
||||
|
||||
- name: Get commit hash
|
||||
|
|
|
|||
2
.github/workflows/tidy-post.yml
vendored
2
.github/workflows/tidy-post.yml
vendored
|
|
@ -1,7 +1,7 @@
|
|||
name: clang-tidy review post comments
|
||||
|
||||
on:
|
||||
workflow_run:
|
||||
workflow_dispatch:
|
||||
workflows: ["clang-tidy-review"]
|
||||
types:
|
||||
- completed
|
||||
|
|
|
|||
3
.gitignore
vendored
3
.gitignore
vendored
|
|
@ -7,6 +7,7 @@
|
|||
.envrc
|
||||
.swiftpm
|
||||
.venv
|
||||
.clang-tidy
|
||||
.vs/
|
||||
.vscode/
|
||||
|
||||
|
|
@ -17,6 +18,7 @@ build-release/
|
|||
build-static/
|
||||
build-cublas/
|
||||
build-opencl/
|
||||
build-metal/
|
||||
build-no-accel/
|
||||
build-sanitize-addr/
|
||||
build-sanitize-thread/
|
||||
|
|
@ -33,6 +35,7 @@ models/*
|
|||
/benchmark-matmult
|
||||
/vdot
|
||||
/Pipfile
|
||||
/libllama.so
|
||||
|
||||
build-info.h
|
||||
arm_neon.h
|
||||
|
|
|
|||
|
|
@ -70,8 +70,9 @@ 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_HIPBLAS "llama: use hipBLAS" OFF)
|
||||
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" ${LLAMA_STANDALONE})
|
||||
|
|
@ -184,7 +185,7 @@ if (LLAMA_CUBLAS)
|
|||
|
||||
enable_language(CUDA)
|
||||
|
||||
set(GGML_CUDA_SOURCES ggml-cuda.cu ggml-cuda.h)
|
||||
set(GGML_SOURCES_CUDA ggml-cuda.cu ggml-cuda.h)
|
||||
|
||||
add_compile_definitions(GGML_USE_CUBLAS)
|
||||
add_compile_definitions(GGML_CUDA_DMMV_X=${LLAMA_CUDA_DMMV_X})
|
||||
|
|
@ -201,12 +202,37 @@ 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)
|
||||
|
||||
|
|
@ -402,8 +428,12 @@ endif()
|
|||
add_library(ggml OBJECT
|
||||
ggml.c
|
||||
ggml.h
|
||||
${GGML_CUDA_SOURCES}
|
||||
${GGML_OPENCL_SOURCES})
|
||||
ggml-quants-k.h
|
||||
ggml-quants-k.c
|
||||
${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
|
||||
|
|
@ -416,18 +446,22 @@ 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")
|
||||
|
|
|
|||
80
Makefile
80
Makefile
|
|
@ -1,5 +1,11 @@
|
|||
# Define the default target now so that it is always the first target
|
||||
default: main quantize quantize-stats perplexity embedding vdot
|
||||
BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot
|
||||
|
||||
ifdef LLAMA_BUILD_SERVER
|
||||
BUILD_TARGETS += server
|
||||
endif
|
||||
|
||||
default: $(BUILD_TARGETS)
|
||||
|
||||
ifndef UNAME_S
|
||||
UNAME_S := $(shell uname -s)
|
||||
|
|
@ -34,11 +40,18 @@ endif
|
|||
#
|
||||
|
||||
# keep standard at C11 and C++11
|
||||
CFLAGS = -I. -O3 -std=c11 -fPIC
|
||||
CXXFLAGS = -I. -I./examples -O3 -std=c++11 -fPIC
|
||||
# -Ofast tends to produce faster code, but may not be available for some compilers.
|
||||
#OPT = -Ofast
|
||||
OPT = -O3
|
||||
CFLAGS = -I. $(OPT) -std=c11 -fPIC
|
||||
CXXFLAGS = -I. -I./examples $(OPT) -std=c++11 -fPIC
|
||||
LDFLAGS =
|
||||
|
||||
ifndef LLAMA_DEBUG
|
||||
ifdef LLAMA_DEBUG
|
||||
CFLAGS += -O0 -g
|
||||
CXXFLAGS += -O0 -g
|
||||
LDFLAGS += -g
|
||||
else
|
||||
CFLAGS += -DNDEBUG
|
||||
CXXFLAGS += -DNDEBUG
|
||||
endif
|
||||
|
|
@ -95,6 +108,7 @@ ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686))
|
|||
#CFLAGS += -mfma -mf16c -mavx
|
||||
#CXXFLAGS += -mfma -mf16c -mavx
|
||||
endif
|
||||
|
||||
ifneq ($(filter ppc64%,$(UNAME_M)),)
|
||||
POWER9_M := $(shell grep "POWER9" /proc/cpuinfo)
|
||||
ifneq (,$(findstring POWER9,$(POWER9_M)))
|
||||
|
|
@ -106,6 +120,7 @@ ifneq ($(filter ppc64%,$(UNAME_M)),)
|
|||
CXXFLAGS += -std=c++23 -DGGML_BIG_ENDIAN
|
||||
endif
|
||||
endif
|
||||
|
||||
ifndef LLAMA_NO_ACCELERATE
|
||||
# Mac M1 - include Accelerate framework.
|
||||
# `-framework Accelerate` works on Mac Intel as well, with negliable performance boost (as of the predict time).
|
||||
|
|
@ -113,7 +128,8 @@ ifndef LLAMA_NO_ACCELERATE
|
|||
CFLAGS += -DGGML_USE_ACCELERATE
|
||||
LDFLAGS += -framework Accelerate
|
||||
endif
|
||||
endif
|
||||
endif # LLAMA_NO_ACCELERATE
|
||||
|
||||
ifdef LLAMA_OPENBLAS
|
||||
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas -I/usr/include/openblas
|
||||
ifneq ($(shell grep -e "Arch Linux" -e "ID_LIKE=arch" /etc/os-release 2>/dev/null),)
|
||||
|
|
@ -121,11 +137,13 @@ ifdef LLAMA_OPENBLAS
|
|||
else
|
||||
LDFLAGS += -lopenblas
|
||||
endif
|
||||
endif
|
||||
endif # LLAMA_OPENBLAS
|
||||
|
||||
ifdef LLAMA_BLIS
|
||||
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/blis -I/usr/include/blis
|
||||
LDFLAGS += -lblis -L/usr/local/lib
|
||||
endif
|
||||
endif # LLAMA_BLIS
|
||||
|
||||
ifdef LLAMA_CUBLAS
|
||||
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
|
||||
CXXFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
|
||||
|
|
@ -146,6 +164,7 @@ endif # LLAMA_CUDA_DMMV_Y
|
|||
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
|
||||
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
|
||||
endif # LLAMA_CUBLAS
|
||||
|
||||
ifdef LLAMA_CLBLAST
|
||||
CFLAGS += -DGGML_USE_CLBLAST
|
||||
CXXFLAGS += -DGGML_USE_CLBLAST
|
||||
|
|
@ -156,9 +175,11 @@ ifdef LLAMA_CLBLAST
|
|||
LDFLAGS += -lclblast -lOpenCL
|
||||
endif
|
||||
OBJS += ggml-opencl.o
|
||||
|
||||
ggml-opencl.o: ggml-opencl.cpp ggml-opencl.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
endif
|
||||
endif # LLAMA_CLBLAST
|
||||
|
||||
ifdef LLAMA_HIPBLAS
|
||||
ROCM_PATH ?= /opt/rocm
|
||||
CC := $(ROCM_PATH)/llvm/bin/clang
|
||||
|
|
@ -176,20 +197,35 @@ ggml-cuda.o: CXXFLAGS += -DGGML_CUDA_DMMV_Y=$(LLAMA_CUDA_DMMV_Y)
|
|||
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
|
||||
$(CXX) $(CXXFLAGS) -x hip -c -o $@ $<
|
||||
endif
|
||||
endif # LLAMA_HIPBLAS
|
||||
|
||||
ifdef LLAMA_METAL
|
||||
CFLAGS += -DGGML_USE_METAL -DGGML_METAL_NDEBUG
|
||||
CXXFLAGS += -DGGML_USE_METAL
|
||||
LDFLAGS += -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
|
||||
OBJS += ggml-metal.o
|
||||
|
||||
ggml-metal.o: ggml-metal.m ggml-metal.h
|
||||
$(CC) $(CFLAGS) -c $< -o $@
|
||||
endif # LLAMA_METAL
|
||||
|
||||
ifneq ($(filter aarch64%,$(UNAME_M)),)
|
||||
# Apple M1, M2, etc.
|
||||
# Raspberry Pi 3, 4, Zero 2 (64-bit)
|
||||
CFLAGS += -mcpu=native
|
||||
CXXFLAGS += -mcpu=native
|
||||
endif
|
||||
|
||||
ifneq ($(filter armv6%,$(UNAME_M)),)
|
||||
# Raspberry Pi 1, Zero
|
||||
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access
|
||||
endif
|
||||
|
||||
ifneq ($(filter armv7%,$(UNAME_M)),)
|
||||
# Raspberry Pi 2
|
||||
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
|
||||
endif
|
||||
|
||||
ifneq ($(filter armv8%,$(UNAME_M)),)
|
||||
# Raspberry Pi 3, 4, Zero 2 (32-bit)
|
||||
CFLAGS += -mfp16-format=ieee -mno-unaligned-access
|
||||
|
|
@ -214,7 +250,10 @@ $(info )
|
|||
# Build library
|
||||
#
|
||||
|
||||
ggml.o: ggml.c ggml.h ggml-cuda.h
|
||||
ggml.o: ggml.c ggml.h ggml-cuda.h ggml-quants-k.h
|
||||
$(CC) $(CFLAGS) -c $< -o $@
|
||||
|
||||
ggml-quants-k.o: ggml-quants-k.c ggml-quants-k.h ggml.h ggml-cuda.h
|
||||
$(CC) $(CFLAGS) -c $< -o $@
|
||||
|
||||
llama.o: llama.cpp ggml.h ggml-cuda.h llama.h llama-util.h
|
||||
|
|
@ -223,37 +262,40 @@ llama.o: llama.cpp ggml.h ggml-cuda.h llama.h llama-util.h
|
|||
common.o: examples/common.cpp examples/common.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
libllama.so: llama.o ggml.o $(OBJS)
|
||||
libllama.so: llama.o ggml.o ggml-quants-k.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
|
||||
|
||||
clean:
|
||||
rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state build-info.h
|
||||
rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server vdot build-info.h
|
||||
|
||||
#
|
||||
# Examples
|
||||
#
|
||||
|
||||
main: examples/main/main.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
main: examples/main/main.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
@echo
|
||||
@echo '==== Run ./main -h for help. ===='
|
||||
@echo
|
||||
|
||||
quantize: examples/quantize/quantize.cpp build-info.h ggml.o llama.o $(OBJS)
|
||||
quantize: examples/quantize/quantize.cpp build-info.h ggml.o ggml-quants-k.o llama.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o llama.o $(OBJS)
|
||||
quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o ggml-quants-k.o llama.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
embedding: examples/embedding/embedding.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
embedding: examples/embedding/embedding.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS)
|
||||
|
||||
build-info.h: $(wildcard .git/index) scripts/build-info.sh
|
||||
@sh scripts/build-info.sh > $@.tmp
|
||||
@if ! cmp -s $@.tmp $@; then \
|
||||
|
|
@ -266,11 +308,11 @@ build-info.h: $(wildcard .git/index) scripts/build-info.sh
|
|||
# Tests
|
||||
#
|
||||
|
||||
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o $(OBJS)
|
||||
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o ggml-quants-k.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
./$@
|
||||
|
||||
vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
|
||||
vdot: pocs/vdot/vdot.cpp ggml.o ggml-quants-k.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
||||
|
||||
.PHONY: tests clean
|
||||
|
|
|
|||
127
README.md
127
README.md
|
|
@ -9,9 +9,11 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
|
|||
|
||||
**Hot topics:**
|
||||
|
||||
- Quantization formats `Q4` and `Q8` have changed again (19 May) - [(info)](https://github.com/ggerganov/llama.cpp/pull/1508)
|
||||
- Quantization formats `Q4` and `Q5` have changed - requantize any old models [(info)](https://github.com/ggerganov/llama.cpp/pull/1405)
|
||||
- [Roadmap May 2023](https://github.com/ggerganov/llama.cpp/discussions/1220)
|
||||
- GPU support with Metal (Apple Silicon): https://github.com/ggerganov/llama.cpp/pull/1642
|
||||
- High-quality 2,3,4,5,6-bit quantization: https://github.com/ggerganov/llama.cpp/pull/1684
|
||||
- Multi-GPU support: https://github.com/ggerganov/llama.cpp/pull/1607
|
||||
- Training LLaMA models from scratch: https://github.com/ggerganov/llama.cpp/pull/1652
|
||||
- CPU threading improvements: https://github.com/ggerganov/llama.cpp/pull/1632
|
||||
|
||||
<details>
|
||||
<summary>Table of Contents</summary>
|
||||
|
|
@ -51,11 +53,10 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
|
|||
The main goal of `llama.cpp` is to run the LLaMA model using 4-bit integer quantization on a MacBook
|
||||
|
||||
- Plain C/C++ implementation without dependencies
|
||||
- Apple silicon first-class citizen - optimized via ARM NEON and Accelerate framework
|
||||
- Apple silicon first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
|
||||
- AVX, AVX2 and AVX512 support for x86 architectures
|
||||
- Mixed F16 / F32 precision
|
||||
- 4-bit, 5-bit and 8-bit integer quantization support
|
||||
- Runs on the CPU
|
||||
- Supports OpenBLAS/Apple BLAS/ARM Performance Lib/ATLAS/BLIS/Intel MKL/NVHPC/ACML/SCSL/SGIMATH and [more](https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors) in BLAS
|
||||
- cuBLAS and CLBlast support
|
||||
|
||||
|
|
@ -236,15 +237,41 @@ In order to build llama.cpp you have three different options.
|
|||
zig build -Drelease-fast
|
||||
```
|
||||
|
||||
### Metal Build
|
||||
|
||||
Using Metal allows the computation to be executed on the GPU for Apple devices:
|
||||
|
||||
- Using `make`:
|
||||
|
||||
```bash
|
||||
LLAMA_METAL=1 make
|
||||
```
|
||||
|
||||
- Using `CMake`:
|
||||
|
||||
```bash
|
||||
mkdir build-metal
|
||||
cd build-metal
|
||||
cmake -DLLAMA_METAL=ON ..
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
When built with Metal support, you can enable GPU inference with the `--gpu-layers|-ngl` command-line argument.
|
||||
Any value larger than 0 will offload the computation to the GPU. For example:
|
||||
|
||||
```bash
|
||||
./main -m ./models/7B/ggml-model-q4_0.bin -n 128 -ngl 1
|
||||
```
|
||||
|
||||
### BLAS Build
|
||||
|
||||
Building the program with BLAS support may lead to some performance improvements in prompt processing using batch sizes higher than 32 (the default is 512). BLAS doesn't affect the normal generation performance. There are currently three different implementations of it:
|
||||
|
||||
- Accelerate Framework:
|
||||
- #### Accelerate Framework:
|
||||
|
||||
This is only available on Mac PCs and it's enabled by default. You can just build using the normal instructions.
|
||||
|
||||
- OpenBLAS:
|
||||
- #### OpenBLAS:
|
||||
|
||||
This provides BLAS acceleration using only the CPU. Make sure to have OpenBLAS installed on your machine.
|
||||
|
||||
|
|
@ -278,11 +305,11 @@ Building the program with BLAS support may lead to some performance improvements
|
|||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
- BLIS
|
||||
- #### BLIS
|
||||
|
||||
Check [BLIS.md](BLIS.md) for more information.
|
||||
|
||||
- Intel MKL
|
||||
- #### Intel MKL
|
||||
|
||||
By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. You may also specify it by:
|
||||
|
||||
|
|
@ -290,10 +317,10 @@ Building the program with BLAS support may lead to some performance improvements
|
|||
mkdir build
|
||||
cd build
|
||||
cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
|
||||
cmake --build . -config Release
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
- cuBLAS
|
||||
- #### cuBLAS
|
||||
|
||||
This provides BLAS acceleration using the CUDA cores of your Nvidia GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager or from here: [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).
|
||||
- Using `make`:
|
||||
|
|
@ -308,9 +335,84 @@ Building the program with BLAS support may lead to some performance improvements
|
|||
cmake .. -DLLAMA_CUBLAS=ON
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
Note: Because llama.cpp uses multiple CUDA streams for matrix multiplication results [are not guaranteed to be reproducible](https://docs.nvidia.com/cuda/cublas/index.html#results-reproducibility). If you need reproducibility, set `GGML_CUDA_MAX_STREAMS` in the file `ggml-cuda.cu` to 1.
|
||||
|
||||
The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used.
|
||||
|
||||
- #### CLBlast
|
||||
|
||||
OpenCL acceleration is provided by the matrix multiplication kernels from the [CLBlast](https://github.com/CNugteren/CLBlast) project and custom kernels for ggml that can generate tokens on the GPU.
|
||||
|
||||
You will need the [OpenCL SDK](https://github.com/KhronosGroup/OpenCL-SDK).
|
||||
- For Ubuntu or Debian, the packages `opencl-headers`, `ocl-icd` may be needed.
|
||||
|
||||
- <details>
|
||||
<summary>Installing the OpenCL SDK from source</summary>
|
||||
|
||||
```sh
|
||||
git clone --recurse-submodules https://github.com/KhronosGroup/OpenCL-SDK.git
|
||||
mkdir OpenCL-SDK/build
|
||||
cd OpenCL-SDK/build
|
||||
cmake .. -DBUILD_DOCS=OFF \
|
||||
-DBUILD_EXAMPLES=OFF \
|
||||
-DBUILD_TESTING=OFF \
|
||||
-DOPENCL_SDK_BUILD_SAMPLES=OFF \
|
||||
-DOPENCL_SDK_TEST_SAMPLES=OFF
|
||||
cmake --build . --config Release
|
||||
cmake --install . --prefix /some/path
|
||||
```
|
||||
</details>
|
||||
|
||||
Installing CLBlast: it may be found in your operating system's packages.
|
||||
|
||||
- <details>
|
||||
<summary>If not, then installing from source:</summary>
|
||||
|
||||
```sh
|
||||
git clone https://github.com/CNugteren/CLBlast.git
|
||||
mkdir CLBlast/build
|
||||
cd CLBLast/build
|
||||
cmake .. -DBUILD_SHARED_LIBS=OFF -DTUNERS=OFF
|
||||
cmake --build . --config Release
|
||||
cmake --install . --prefix /some/path
|
||||
```
|
||||
|
||||
Where `/some/path` is where the built library will be installed (default is `/usr/local`).
|
||||
</details>
|
||||
|
||||
Building:
|
||||
|
||||
- Build with make:
|
||||
```sh
|
||||
make LLAMA_CLBLAST=1
|
||||
```
|
||||
- CMake:
|
||||
```sh
|
||||
mkdir build
|
||||
cd build
|
||||
cmake .. -DLLAMA_CLBLAST=ON -DCLBlast_dir=/some/path
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
Running:
|
||||
|
||||
The CLBlast build supports `--gpu-layers|-ngl` like the CUDA version does.
|
||||
|
||||
To select the correct platform (driver) and device (GPU), you can use the environment variables `GGML_OPENCL_PLATFORM` and `GGML_OPENCL_DEVICE`.
|
||||
The selection can be a number (starting from 0) or a text string to search:
|
||||
|
||||
```sh
|
||||
GGML_OPENCL_PLATFORM=1 ./main ...
|
||||
GGML_OPENCL_DEVICE=2 ./main ...
|
||||
GGML_OPENCL_PLATFORM=Intel ./main ...
|
||||
GGML_OPENCL_PLATFORM=AMD GGML_OPENCL_DEVICE=1 ./main ...
|
||||
```
|
||||
|
||||
The default behavior is to find the first GPU device, but when it is an integrated GPU on a laptop, for instance, the selectors are useful.
|
||||
Using the variables it is possible to select a CPU-based driver as well, if so desired.
|
||||
|
||||
You can get a list of platforms and devices from the `clinfo -l` command, etc.
|
||||
|
||||
### Prepare Data & Run
|
||||
|
||||
```bash
|
||||
|
|
@ -582,3 +684,4 @@ docker run -v /path/to/models:/models ghcr.io/ggerganov/llama.cpp:light -m /mode
|
|||
### Docs
|
||||
|
||||
- [GGML tips & tricks](https://github.com/ggerganov/llama.cpp/wiki/GGML-Tips-&-Tricks)
|
||||
- [Performance troubleshooting](./docs/token_generation_performance_tips.md)
|
||||
|
|
|
|||
|
|
@ -4,7 +4,9 @@ import argparse
|
|||
|
||||
import convert
|
||||
|
||||
parser = argparse.ArgumentParser(description='Convert a LLaMA model checkpoint to a ggml compatible file')
|
||||
parser = argparse.ArgumentParser(
|
||||
description="""[DEPRECATED - use `convert.py` instead]
|
||||
Convert a LLaMA model checkpoint to a ggml compatible file""")
|
||||
parser.add_argument('dir_model', help='directory containing the model checkpoint')
|
||||
parser.add_argument('ftype', help='file type (0: float32, 1: float16)', type=int, choices=[0, 1], default=1)
|
||||
args = parser.parse_args()
|
||||
|
|
|
|||
40
docs/token_generation_performance_tips.md
Normal file
40
docs/token_generation_performance_tips.md
Normal file
|
|
@ -0,0 +1,40 @@
|
|||
# Token generation performance troubleshooting
|
||||
|
||||
## Verifying that the model is running on the GPU with cuBLAS
|
||||
Make sure you compiled llama with the correct env variables according to [this guide](../README.md#cublas), so that llama accepts the `-ngl N` (or `--n-gpu-layers N`) flag. When running llama, you may configure `N` to be very large, and llama will offload the maximum possible number of layers to the GPU, even if it's less than the number you configured. For example:
|
||||
```shell
|
||||
./main -m "path/to/model.bin" -ngl 200000 -p "Please sir, may I have some "
|
||||
```
|
||||
|
||||
When running llama, before it starts the inference work, it will output diagnostic information that shows whether cuBLAS is offloading work to the GPU. Look for these lines:
|
||||
```shell
|
||||
llama_model_load_internal: [cublas] offloading 60 layers to GPU
|
||||
llama_model_load_internal: [cublas] offloading output layer to GPU
|
||||
llama_model_load_internal: [cublas] total VRAM used: 17223 MB
|
||||
... rest of inference
|
||||
```
|
||||
|
||||
If you see these lines, then the GPU is being used.
|
||||
|
||||
## Verifying that the CPU is not oversaturated
|
||||
llama accepts a `-t N` (or `--threads N`) parameter. It's extremely important that this parameter is not too large. If your token generation is extremely slow, try setting this number to 1. If this significantly improves your token generation speed, then your CPU is being oversaturated and you need to explicitly set this parameter to the number of the physicial CPU cores on your machine (even if you utilize a GPU). If in doubt, start with 1 and double the amount until you hit a performance bottleneck, then scale the number down.
|
||||
|
||||
# Example of runtime flags effect on inference speed benchmark
|
||||
These runs were tested on the following machine:
|
||||
GPU: A6000 (48GB VRAM)
|
||||
CPU: 7 physical cores
|
||||
RAM: 32GB
|
||||
|
||||
Model: `TheBloke_Wizard-Vicuna-30B-Uncensored-GGML/Wizard-Vicuna-30B-Uncensored.ggmlv3.q4_0.bin` (30B parameters, 4bit quantization, GGML)
|
||||
|
||||
Run command: `./main -m "path/to/model.bin" -p "-p "An extremely detailed description of the 10 best ethnic dishes will follow, with recipes: " -n 1000 [additional benchmark flags]`
|
||||
|
||||
Result:
|
||||
|
||||
| command | tokens/second (higher is better) |
|
||||
| - | - |
|
||||
| -ngl 2000000 | N/A (less than 0.1) |
|
||||
| -t 7 | 1.7 |
|
||||
| -t 1 -ngl 2000000 | 5.5 |
|
||||
| -t 7 -ngl 2000000 | 8.7 |
|
||||
| -t 4 -ngl 2000000 | 9.1 |
|
||||
|
|
@ -37,6 +37,9 @@ else()
|
|||
add_subdirectory(save-load-state)
|
||||
add_subdirectory(benchmark)
|
||||
add_subdirectory(baby-llama)
|
||||
if (LLAMA_METAL)
|
||||
add_subdirectory(metal)
|
||||
endif()
|
||||
if (LLAMA_BUILD_SERVER)
|
||||
add_subdirectory(server)
|
||||
endif()
|
||||
|
|
|
|||
|
|
@ -251,6 +251,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
|
|||
break;
|
||||
}
|
||||
params.model = argv[i];
|
||||
} else if (arg == "-a" || arg == "--alias") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
params.model_alias = argv[i];
|
||||
} else if (arg == "--lora") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
|
|
@ -283,11 +289,18 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
|
|||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
|
||||
params.n_gpu_layers = std::stoi(argv[i]);
|
||||
#else
|
||||
fprintf(stderr, "warning: not compiled with GPU offload support, --n-gpu-layers option will be ignored\n");
|
||||
fprintf(stderr, "warning: see main README.md for information on enabling GPU BLAS support\n");
|
||||
#endif
|
||||
} else if (arg == "--no-mmap") {
|
||||
params.use_mmap = false;
|
||||
} else if (arg == "--mtest") {
|
||||
params.mem_test = true;
|
||||
} else if (arg == "--export") {
|
||||
params.export_cgraph = true;
|
||||
} else if (arg == "--verbose-prompt") {
|
||||
params.verbose_prompt = true;
|
||||
} else if (arg == "-r" || arg == "--reverse-prompt") {
|
||||
|
|
@ -410,7 +423,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
|
|||
fprintf(stderr, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
|
||||
fprintf(stderr, " --ignore-eos ignore end of stream token and continue generating (implies --logit-bias 2-inf)\n");
|
||||
fprintf(stderr, " --no-penalize-nl do not penalize newline token\n");
|
||||
fprintf(stderr, " --memory-f32 use f32 instead of f16 for memory key+value\n");
|
||||
fprintf(stderr, " --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n");
|
||||
fprintf(stderr, " not recommended: doubles context memory required and no measurable increase in quality\n");
|
||||
fprintf(stderr, " --temp N temperature (default: %.1f)\n", (double)params.temp);
|
||||
fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
|
||||
fprintf(stderr, " --perplexity compute perplexity over the prompt\n");
|
||||
|
|
@ -421,9 +435,12 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
|
|||
if (llama_mmap_supported()) {
|
||||
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
|
||||
}
|
||||
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
|
||||
fprintf(stderr, " -ngl N, --n-gpu-layers N\n");
|
||||
fprintf(stderr, " number of layers to store in VRAM\n");
|
||||
#endif
|
||||
fprintf(stderr, " --mtest compute maximum memory usage\n");
|
||||
fprintf(stderr, " --export export the computation graph to 'llama.ggml'\n");
|
||||
fprintf(stderr, " --verbose-prompt print prompt before generation\n");
|
||||
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
|
||||
fprintf(stderr, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n");
|
||||
|
|
|
|||
|
|
@ -45,6 +45,7 @@ struct gpt_params {
|
|||
float mirostat_eta = 0.10f; // learning rate
|
||||
|
||||
std::string model = "models/7B/ggml-model.bin"; // model path
|
||||
std::string model_alias = "unknown"; // model alias
|
||||
std::string prompt = "";
|
||||
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
|
||||
std::string input_prefix = ""; // string to prefix user inputs with
|
||||
|
|
@ -70,6 +71,7 @@ struct gpt_params {
|
|||
bool use_mmap = true; // use mmap for faster loads
|
||||
bool use_mlock = false; // use mlock to keep model in memory
|
||||
bool mem_test = false; // compute maximum memory usage
|
||||
bool export_cgraph = false; // export the computation graph
|
||||
bool verbose_prompt = false; // print prompt tokens before generation
|
||||
};
|
||||
|
||||
|
|
|
|||
|
|
@ -69,8 +69,8 @@ In this section, we cover the most commonly used options for running the `main`
|
|||
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`).
|
||||
- `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses.
|
||||
- `-ins, --instruct`: Run the program in instruction mode, which is particularly useful when working with Alpaca models.
|
||||
- `-n N, --n_predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text.
|
||||
- `-c N, --ctx_size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference.
|
||||
- `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text.
|
||||
- `-c N, --ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference.
|
||||
|
||||
## Input Prompts
|
||||
|
||||
|
|
@ -136,9 +136,9 @@ During text generation, LLaMA models have a limited context size, which means th
|
|||
|
||||
### Context Size
|
||||
|
||||
The `--ctx_size` option allows you to set the size of the prompt context used by the LLaMA models during text generation. A larger context size helps the model to better comprehend and generate responses for longer input or conversations.
|
||||
The `--ctx-size` option allows you to set the size of the prompt context used by the LLaMA models during text generation. A larger context size helps the model to better comprehend and generate responses for longer input or conversations.
|
||||
|
||||
- `-c N, --ctx_size N`: Set the size of the prompt context (default: 512). The LLaMA models were built with a context of 2048, which will yield the best results on longer input/inference. However, increasing the context size beyond 2048 may lead to unpredictable results.
|
||||
- `-c N, --ctx-size N`: Set the size of the prompt context (default: 512). The LLaMA models were built with a context of 2048, which will yield the best results on longer input/inference. However, increasing the context size beyond 2048 may lead to unpredictable results.
|
||||
|
||||
### Keep Prompt
|
||||
|
||||
|
|
@ -146,7 +146,7 @@ The `--keep` option allows users to retain the original prompt when the model ru
|
|||
|
||||
- `--keep N`: Specify the number of tokens from the initial prompt to retain when the model resets its internal context. By default, this value is set to 0 (meaning no tokens are kept). Use `-1` to retain all tokens from the initial prompt.
|
||||
|
||||
By utilizing context management options like `--ctx_size` and `--keep`, you can maintain a more coherent and consistent interaction with the LLaMA models, ensuring that the generated text remains relevant to the original prompt or conversation.
|
||||
By utilizing context management options like `--ctx-size` and `--keep`, you can maintain a more coherent and consistent interaction with the LLaMA models, ensuring that the generated text remains relevant to the original prompt or conversation.
|
||||
|
||||
## Generation Flags
|
||||
|
||||
|
|
@ -154,11 +154,11 @@ The following options allow you to control the text generation process and fine-
|
|||
|
||||
### Number of Tokens to Predict
|
||||
|
||||
- `-n N, --n_predict N`: Set the number of tokens to predict when generating text (default: 128, -1 = infinity).
|
||||
- `-n N, --n-predict N`: Set the number of tokens to predict when generating text (default: 128, -1 = infinity).
|
||||
|
||||
The `--n_predict` option controls the number of tokens the model generates in response to the input prompt. By adjusting this value, you can influence the length of the generated text. A higher value will result in longer text, while a lower value will produce shorter text. A value of -1 will cause text to be generated without limit.
|
||||
The `--n-predict` option controls the number of tokens the model generates in response to the input prompt. By adjusting this value, you can influence the length of the generated text. A higher value will result in longer text, while a lower value will produce shorter text. A value of -1 will cause text to be generated without limit.
|
||||
|
||||
It is important to note that the generated text may be shorter than the specified number of tokens if an End-of-Sequence (EOS) token or a reverse prompt is encountered. In interactive mode text generation will pause and control will be returned to the user. In non-interactive mode, the program will end. In both cases, the text generation may stop before reaching the specified `n_predict` value. If you want the model to keep going without ever producing End-of-Sequence on its own, you can use the `--ignore-eos` parameter.
|
||||
It is important to note that the generated text may be shorter than the specified number of tokens if an End-of-Sequence (EOS) token or a reverse prompt is encountered. In interactive mode text generation will pause and control will be returned to the user. In non-interactive mode, the program will end. In both cases, the text generation may stop before reaching the specified `n-predict` value. If you want the model to keep going without ever producing End-of-Sequence on its own, you can use the `--ignore-eos` parameter.
|
||||
|
||||
### Temperature
|
||||
|
||||
|
|
@ -170,33 +170,33 @@ Example usage: `--temp 0.5`
|
|||
|
||||
### Repeat Penalty
|
||||
|
||||
- `--repeat_penalty N`: Control the repetition of token sequences in the generated text (default: 1.1).
|
||||
- `--repeat_last_n N`: Last n tokens to consider for penalizing repetition (default: 64, 0 = disabled, -1 = ctx_size).
|
||||
- `--repeat-penalty N`: Control the repetition of token sequences in the generated text (default: 1.1).
|
||||
- `--repeat-last-n N`: Last n tokens to consider for penalizing repetition (default: 64, 0 = disabled, -1 = ctx-size).
|
||||
- `--no-penalize-nl`: Disable penalization for newline tokens when applying the repeat penalty.
|
||||
|
||||
The `repeat_penalty` option helps prevent the model from generating repetitive or monotonous text. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. The default value is 1.1.
|
||||
The `repeat-penalty` option helps prevent the model from generating repetitive or monotonous text. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. The default value is 1.1.
|
||||
|
||||
The `repeat_last_n` option controls the number of tokens in the history to consider for penalizing repetition. A larger value will look further back in the generated text to prevent repetitions, while a smaller value will only consider recent tokens. A value of 0 disables the penalty, and a value of -1 sets the number of tokens considered equal to the context size (`ctx_size`).
|
||||
The `repeat-last-n` option controls the number of tokens in the history to consider for penalizing repetition. A larger value will look further back in the generated text to prevent repetitions, while a smaller value will only consider recent tokens. A value of 0 disables the penalty, and a value of -1 sets the number of tokens considered equal to the context size (`ctx-size`).
|
||||
|
||||
Use the `--no-penalize-nl` option to disable newline penalization when applying the repeat penalty. This option is particularly useful for generating chat conversations, dialogues, code, poetry, or any text where newline tokens play a significant role in structure and formatting. Disabling newline penalization helps maintain the natural flow and intended formatting in these specific use cases.
|
||||
|
||||
Example usage: `--repeat_penalty 1.15 --repeat_last_n 128 --no-penalize-nl`
|
||||
Example usage: `--repeat-penalty 1.15 --repeat-last-n 128 --no-penalize-nl`
|
||||
|
||||
### Top-K Sampling
|
||||
|
||||
- `--top_k N`: Limit the next token selection to the K most probable tokens (default: 40).
|
||||
- `--top-k N`: Limit the next token selection to the K most probable tokens (default: 40).
|
||||
|
||||
Top-k sampling is a text generation method that selects the next token only from the top k most likely tokens predicted by the model. It helps reduce the risk of generating low-probability or nonsensical tokens, but it may also limit the diversity of the output. A higher value for top_k (e.g., 100) will consider more tokens and lead to more diverse text, while a lower value (e.g., 10) will focus on the most probable tokens and generate more conservative text. The default value is 40.
|
||||
Top-k sampling is a text generation method that selects the next token only from the top k most likely tokens predicted by the model. It helps reduce the risk of generating low-probability or nonsensical tokens, but it may also limit the diversity of the output. A higher value for top-k (e.g., 100) will consider more tokens and lead to more diverse text, while a lower value (e.g., 10) will focus on the most probable tokens and generate more conservative text. The default value is 40.
|
||||
|
||||
Example usage: `--top_k 30`
|
||||
Example usage: `--top-k 30`
|
||||
|
||||
### Top-P Sampling
|
||||
|
||||
- `--top_p N`: Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P (default: 0.9).
|
||||
- `--top-p N`: Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P (default: 0.9).
|
||||
|
||||
Top-p sampling, also known as nucleus sampling, is another text generation method that selects the next token from a subset of tokens that together have a cumulative probability of at least p. This method provides a balance between diversity and quality by considering both the probabilities of tokens and the number of tokens to sample from. A higher value for top_p (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. The default value is 0.9.
|
||||
Top-p sampling, also known as nucleus sampling, is another text generation method that selects the next token from a subset of tokens that together have a cumulative probability of at least p. This method provides a balance between diversity and quality by considering both the probabilities of tokens and the number of tokens to sample from. A higher value for top-p (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. The default value is 0.9.
|
||||
|
||||
Example usage: `--top_p 0.95`
|
||||
Example usage: `--top-p 0.95`
|
||||
|
||||
### Tail Free Sampling (TFS)
|
||||
|
||||
|
|
@ -217,16 +217,16 @@ Example usage: `--typical 0.9`
|
|||
### Mirostat Sampling
|
||||
|
||||
- `--mirostat N`: Enable Mirostat sampling, controlling perplexity during text generation (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0).
|
||||
- `--mirostat_lr N`: Set the Mirostat learning rate, parameter eta (default: 0.1).
|
||||
- `--mirostat_ent N`: Set the Mirostat target entropy, parameter tau (default: 5.0).
|
||||
- `--mirostat-lr N`: Set the Mirostat learning rate, parameter eta (default: 0.1).
|
||||
- `--mirostat-ent N`: Set the Mirostat target entropy, parameter tau (default: 5.0).
|
||||
|
||||
Mirostat is an algorithm that actively maintains the quality of generated text within a desired range during text generation. It aims to strike a balance between coherence and diversity, avoiding low-quality output caused by excessive repetition (boredom traps) or incoherence (confusion traps).
|
||||
|
||||
The `--mirostat_lr` option sets the Mirostat learning rate (eta). The learning rate influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. The default value is `0.1`.
|
||||
The `--mirostat-lr` option sets the Mirostat learning rate (eta). The learning rate influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. The default value is `0.1`.
|
||||
|
||||
The `--mirostat_ent` option sets the Mirostat target entropy (tau), which represents the desired perplexity value for the generated text. Adjusting the target entropy allows you to control the balance between coherence and diversity in the generated text. A lower value will result in more focused and coherent text, while a higher value will lead to more diverse and potentially less coherent text. The default value is `5.0`.
|
||||
The `--mirostat-ent` option sets the Mirostat target entropy (tau), which represents the desired perplexity value for the generated text. Adjusting the target entropy allows you to control the balance between coherence and diversity in the generated text. A lower value will result in more focused and coherent text, while a higher value will lead to more diverse and potentially less coherent text. The default value is `5.0`.
|
||||
|
||||
Example usage: `--mirostat 2 --mirostat_lr 0.05 --mirostat_ent 3.0`
|
||||
Example usage: `--mirostat 2 --mirostat-lr 0.05 --mirostat-ent 3.0`
|
||||
|
||||
### Logit Bias
|
||||
|
||||
|
|
@ -264,11 +264,11 @@ These options help improve the performance and memory usage of the LLaMA models.
|
|||
|
||||
### Memory Float 32
|
||||
|
||||
- `--memory_f32`: Use 32-bit floats instead of 16-bit floats for memory key+value, allowing higher quality inference at the cost of higher memory usage.
|
||||
- `--memory-f32`: Use 32-bit floats instead of 16-bit floats for memory key+value. This doubles the context memory requirement and cached prompt file size but does not appear to increase generation quality in a measurable way. Not recommended.
|
||||
|
||||
### Batch Size
|
||||
|
||||
- `-b N, --batch_size N`: Set the batch size for prompt processing (default: 512). This large batch size benefits users who have BLAS installed and enabled it during the build. If you don't have BLAS enabled ("BLAS=0"), you can use a smaller number, such as 8, to see the prompt progress as it's evaluated in some situations.
|
||||
- `-b N, --batch-size N`: Set the batch size for prompt processing (default: 512). This large batch size benefits users who have BLAS installed and enabled it during the build. If you don't have BLAS enabled ("BLAS=0"), you can use a smaller number, such as 8, to see the prompt progress as it's evaluated in some situations.
|
||||
|
||||
### Prompt Caching
|
||||
|
||||
|
|
@ -285,5 +285,6 @@ These options provide extra functionality and customization when running the LLa
|
|||
- `-h, --help`: Display a help message showing all available options and their default values. This is particularly useful for checking the latest options and default values, as they can change frequently, and the information in this document may become outdated.
|
||||
- `--verbose-prompt`: Print the prompt before generating text.
|
||||
- `--mtest`: Test the model's functionality by running a series of tests to ensure it's working properly.
|
||||
- `-ngl N, --n-gpu-layers N`: When compiled with appropriate support (currently CLBlast or cuBLAS), this option allows offloading some layers to the GPU for computation. Generally results in increased performance.
|
||||
- `--lora FNAME`: Apply a LoRA (Low-Rank Adaptation) adapter to the model (implies --no-mmap). This allows you to adapt the pretrained model to specific tasks or domains.
|
||||
- `--lora-base FNAME`: Optional model to use as a base for the layers modified by the LoRA adapter. This flag is used in conjunction with the `--lora` flag, and specifies the base model for the adaptation.
|
||||
|
|
|
|||
|
|
@ -134,6 +134,13 @@ int main(int argc, char ** argv) {
|
|||
return 0;
|
||||
}
|
||||
|
||||
// export the cgraph and exit
|
||||
if (params.export_cgraph) {
|
||||
llama_eval_export(ctx, "llama.ggml");
|
||||
llama_free(ctx);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
std::string path_session = params.path_prompt_cache;
|
||||
std::vector<llama_token> session_tokens;
|
||||
|
|
@ -202,6 +209,13 @@ int main(int argc, char ** argv) {
|
|||
}
|
||||
}
|
||||
|
||||
// if we will use the cache for the full prompt without reaching the end of the cache, force
|
||||
// reevaluation of the last token token to recalculate the cached logits
|
||||
if (!embd_inp.empty() && n_matching_session_tokens == embd_inp.size() &&
|
||||
session_tokens.size() > embd_inp.size()) {
|
||||
session_tokens.resize(embd_inp.size() - 1);
|
||||
}
|
||||
|
||||
// number of tokens to keep when resetting context
|
||||
if (params.n_keep < 0 || params.n_keep > (int) embd_inp.size() || params.instruct) {
|
||||
params.n_keep = (int)embd_inp.size();
|
||||
|
|
|
|||
3
examples/metal/CMakeLists.txt
Normal file
3
examples/metal/CMakeLists.txt
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
set(TEST_TARGET metal)
|
||||
add_executable(${TEST_TARGET} metal.cpp)
|
||||
target_link_libraries(${TEST_TARGET} PRIVATE ggml)
|
||||
102
examples/metal/metal.cpp
Normal file
102
examples/metal/metal.cpp
Normal file
|
|
@ -0,0 +1,102 @@
|
|||
// Evaluate a statically exported ggml computation graph with Metal
|
||||
//
|
||||
// - First, export a LLaMA graph:
|
||||
//
|
||||
// $ ./bin/main -m ../models/7B/ggml-model-q4_0.bin --export
|
||||
//
|
||||
// - Run this tool to evaluate the exported graph:
|
||||
//
|
||||
// $ ./bin/metal llama.ggml
|
||||
//
|
||||
// The purpose of this tool is mostly for debugging and demonstration purposes.
|
||||
// The main limitation of exporting computation graphs is that their sizes are static which often
|
||||
// can be a problem for real-world applications.
|
||||
//
|
||||
|
||||
#include "ggml.h"
|
||||
#include "ggml-metal.h"
|
||||
|
||||
#include <cstdio>
|
||||
#include <cstring>
|
||||
#include <cstdlib>
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
ggml_time_init();
|
||||
|
||||
if (argc != 2) {
|
||||
fprintf(stderr, "Usage: %s llama.ggml\n", argv[0]);
|
||||
return -1;
|
||||
}
|
||||
|
||||
const char * fname_cgraph = argv[1];
|
||||
|
||||
// load the compute graph
|
||||
struct ggml_context * ctx_data = NULL;
|
||||
struct ggml_context * ctx_eval = NULL;
|
||||
|
||||
struct ggml_cgraph gf = ggml_graph_import(fname_cgraph, &ctx_data, &ctx_eval);
|
||||
gf.n_threads = 1;
|
||||
|
||||
// this allocates all Metal resources and memory buffers
|
||||
auto * ctx_metal = ggml_metal_init();
|
||||
|
||||
ggml_metal_add_buffer(ctx_metal, "data", ggml_get_mem_buffer(ctx_data), ggml_get_mem_size(ctx_data));
|
||||
ggml_metal_add_buffer(ctx_metal, "eval", ggml_get_mem_buffer(ctx_eval), ggml_get_mem_size(ctx_eval));
|
||||
|
||||
// main
|
||||
{
|
||||
struct ggml_tensor * input = ggml_graph_get_tensor(&gf, "embd");
|
||||
*(int32_t *) input->data = 1; // BOS
|
||||
|
||||
ggml_metal_set_tensor(ctx_metal, input);
|
||||
|
||||
// warmup
|
||||
ggml_metal_graph_compute(ctx_metal, &gf);
|
||||
|
||||
const int n_iter = 16;
|
||||
|
||||
const int64_t t0 = ggml_time_us();
|
||||
|
||||
// the actual inference happens here
|
||||
for (int i = 0; i < n_iter; ++i) {
|
||||
ggml_metal_graph_compute(ctx_metal, &gf);
|
||||
}
|
||||
|
||||
const int64_t t1 = ggml_time_us();
|
||||
|
||||
printf("time: %.2f ms, %.2f ms/tok\n", (t1 - t0) / 1000.0, (t1 - t0) / 1000.0 / n_iter);
|
||||
}
|
||||
|
||||
// debug output
|
||||
{
|
||||
struct ggml_tensor * logits = gf.nodes[gf.n_nodes - 1];
|
||||
ggml_metal_get_tensor(ctx_metal, logits);
|
||||
|
||||
float * ptr = (float *) ggml_get_data(logits);
|
||||
|
||||
printf("logits: ");
|
||||
for (int i = 0; i < 10; i++) {
|
||||
printf("%8.4f ", ptr[i]);
|
||||
}
|
||||
printf("\n");
|
||||
int imax = 0;
|
||||
double sum = 0.0;
|
||||
double vmax = -1e9;
|
||||
for (int i = 0; i < 32000; i++) {
|
||||
sum += (double) ptr[i];
|
||||
if (ptr[i] > vmax) {
|
||||
vmax = ptr[i];
|
||||
imax = i;
|
||||
}
|
||||
}
|
||||
printf("sum: %f, imax = %d, vmax = %f\n", sum, imax, vmax);
|
||||
}
|
||||
|
||||
ggml_metal_free(ctx_metal);
|
||||
|
||||
ggml_free(ctx_data);
|
||||
ggml_free(ctx_eval);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -282,8 +282,9 @@ int main(int argc, char ** argv) {
|
|||
break;
|
||||
}
|
||||
int j;
|
||||
for (j = 0; j < GGML_TYPE_COUNT && strcmp(argv[i], ggml_type_name((ggml_type) j)) != 0; j++) {
|
||||
// find match
|
||||
for (j = 0; j < GGML_TYPE_COUNT; ++j) {
|
||||
const auto * name = ggml_type_name((ggml_type) j);
|
||||
if (name && strcmp(argv[i], name) == 0) break;
|
||||
}
|
||||
if (j < GGML_TYPE_COUNT) {
|
||||
params.include_types.push_back((ggml_type) j);
|
||||
|
|
|
|||
|
|
@ -12,6 +12,18 @@ static const std::map<std::string, llama_ftype> LLAMA_FTYPE_MAP = {
|
|||
{"q5_0", LLAMA_FTYPE_MOSTLY_Q5_0},
|
||||
{"q5_1", LLAMA_FTYPE_MOSTLY_Q5_1},
|
||||
{"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
|
||||
{"q2_K", LLAMA_FTYPE_MOSTLY_Q2_K},
|
||||
{"q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M},
|
||||
{"q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S},
|
||||
{"q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M},
|
||||
{"q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L},
|
||||
{"q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M},
|
||||
{"q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S},
|
||||
{"q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M},
|
||||
{"q5_K", LLAMA_FTYPE_MOSTLY_Q5_K_M},
|
||||
{"q5_K_S", LLAMA_FTYPE_MOSTLY_Q5_K_S},
|
||||
{"q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M},
|
||||
{"q6_K", LLAMA_FTYPE_MOSTLY_Q6_K},
|
||||
};
|
||||
|
||||
bool try_parse_ftype(const std::string & ftype_str, llama_ftype & ftype, std::string & ftype_str_out) {
|
||||
|
|
|
|||
|
|
@ -285,7 +285,8 @@ Test();
|
|||
## Common Options
|
||||
|
||||
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`).
|
||||
- `-c N, --ctx_size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference.
|
||||
- `-c N, --ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference.
|
||||
- `-ngl N, --n-gpu-layers N`: When compiled with appropriate support (currently CLBlast or cuBLAS), this option allows offloading some layers to the GPU for computation. Generally results in increased performance.
|
||||
- `--embedding`: Enable the embedding mode. **Completion function doesn't work in this mode**.
|
||||
- `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`;
|
||||
- `--port`: Set the port to listen. Default: `8080`.
|
||||
|
|
@ -304,7 +305,7 @@ The RNG seed is used to initialize the random number generator that influences t
|
|||
|
||||
### Memory Float 32
|
||||
|
||||
- `--memory_f32`: Use 32-bit floats instead of 16-bit floats for memory key+value, allowing higher quality inference at the cost of higher memory usage.
|
||||
- `--memory-f32`: Use 32-bit floats instead of 16-bit floats for memory key+value. This doubles the context memory requirement but does not appear to increase generation quality in a measurable way. Not recommended.
|
||||
|
||||
## Limitations:
|
||||
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ struct llama_server_context
|
|||
std::vector<llama_token> prompt_tokens = ::llama_tokenize(ctx, params.prompt, true);
|
||||
// compare the evaluated prompt with the new prompt
|
||||
int new_prompt_len = 0;
|
||||
for (int i = 0;i < prompt_tokens.size(); i++) {
|
||||
for (size_t i = 0; i < prompt_tokens.size(); i++) {
|
||||
if (i < processed_tokens.size() &&
|
||||
processed_tokens[i] == prompt_tokens[i])
|
||||
{
|
||||
|
|
@ -71,7 +71,7 @@ struct llama_server_context
|
|||
{
|
||||
embd_inp.push_back(prompt_tokens[i]);
|
||||
if(new_prompt_len == 0) {
|
||||
if(i - 1 < n_past) {
|
||||
if(int32_t(i) - 1 < n_past) {
|
||||
processed_tokens.erase(processed_tokens.begin() + i, processed_tokens.end());
|
||||
}
|
||||
// Evaluate the new fragment prompt from the last token processed.
|
||||
|
|
@ -136,7 +136,7 @@ struct llama_server_context
|
|||
{
|
||||
// out of user input, sample next token
|
||||
const float temp = params.temp;
|
||||
const int32_t top_k = params.top_k <= 0 ? llama_n_vocab(ctx) : params.top_k;
|
||||
// const int32_t top_k = params.top_k <= 0 ? llama_n_vocab(ctx) : params.top_k;
|
||||
const float top_p = params.top_p;
|
||||
const float tfs_z = params.tfs_z;
|
||||
const float typical_p = params.typical_p;
|
||||
|
|
@ -306,12 +306,12 @@ struct llama_server_context
|
|||
// Avoid add the no show words to the response
|
||||
for (std::vector<llama_token> word_tokens : no_show_words)
|
||||
{
|
||||
int match_token = 1;
|
||||
size_t match_token = 1;
|
||||
if (tokens_predicted.front() == word_tokens.front())
|
||||
{
|
||||
bool execute_matching = true;
|
||||
if (tokens_predicted.size() > 1) { // if previus tokens had been tested
|
||||
for (int i = 1; i < word_tokens.size(); i++)
|
||||
for (size_t i = 1; i < word_tokens.size(); i++)
|
||||
{
|
||||
if (i >= tokens_predicted.size()) {
|
||||
match_token = i;
|
||||
|
|
@ -385,7 +385,9 @@ void server_print_usage(int /*argc*/, char **argv, const gpt_params ¶ms)
|
|||
fprintf(stderr, "options:\n");
|
||||
fprintf(stderr, " -h, --help show this help message and exit\n");
|
||||
fprintf(stderr, " -s SEED, --seed SEED RNG seed (default: -1, use random seed for < 0)\n");
|
||||
fprintf(stderr, " --memory_f32 use f32 instead of f16 for memory key+value\n");
|
||||
fprintf(stderr, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
|
||||
fprintf(stderr, " --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n");
|
||||
fprintf(stderr, " not recommended: doubles context memory required and no measurable increase in quality\n");
|
||||
fprintf(stderr, " --embedding enable embedding mode\n");
|
||||
fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
|
||||
if (llama_mlock_supported())
|
||||
|
|
@ -396,12 +398,16 @@ void server_print_usage(int /*argc*/, char **argv, const gpt_params ¶ms)
|
|||
{
|
||||
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
|
||||
}
|
||||
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
|
||||
fprintf(stderr, " -ngl N, --n-gpu-layers N\n");
|
||||
fprintf(stderr, " number of layers to store in VRAM\n");
|
||||
#endif
|
||||
fprintf(stderr, " -m FNAME, --model FNAME\n");
|
||||
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
|
||||
fprintf(stderr, " -host ip address to listen (default 127.0.0.1)\n");
|
||||
fprintf(stderr, " -port PORT port to listen (default 8080)\n");
|
||||
fprintf(stderr, " -a ALIAS, --alias ALIAS\n");
|
||||
fprintf(stderr, " set an alias for the model, will be added as `model` field in completion response\n");
|
||||
fprintf(stderr, " --host ip address to listen (default 127.0.0.1)\n");
|
||||
fprintf(stderr, " --port PORT port to listen (default 8080)\n");
|
||||
fprintf(stderr, "\n");
|
||||
}
|
||||
|
||||
|
|
@ -453,6 +459,15 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
|
|||
}
|
||||
params.model = argv[i];
|
||||
}
|
||||
else if (arg == "-a" || arg == "--alias")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
params.model_alias = argv[i];
|
||||
}
|
||||
else if (arg == "--embedding")
|
||||
{
|
||||
params.embedding = true;
|
||||
|
|
@ -462,7 +477,7 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
|
|||
server_print_usage(argc, argv, default_params);
|
||||
exit(0);
|
||||
}
|
||||
else if (arg == "-c" || arg == "--ctx_size")
|
||||
else if (arg == "-c" || arg == "--ctx-size" || arg == "--ctx_size")
|
||||
{
|
||||
if (++i >= argc)
|
||||
{
|
||||
|
|
@ -471,7 +486,7 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
|
|||
}
|
||||
params.n_ctx = std::stoi(argv[i]);
|
||||
}
|
||||
else if (arg == "--memory_f32")
|
||||
else if (arg == "--memory-f32" || arg == "--memory_f32")
|
||||
{
|
||||
params.memory_f16 = false;
|
||||
}
|
||||
|
|
@ -482,7 +497,12 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
|
|||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
|
||||
params.n_gpu_layers = std::stoi(argv[i]);
|
||||
#else
|
||||
fprintf(stderr, "warning: not compiled with GPU offload support, --n-gpu-layers option will be ignored\n");
|
||||
fprintf(stderr, "warning: see main README.md for information on enabling GPU BLAS support\n");
|
||||
#endif
|
||||
}
|
||||
else
|
||||
{
|
||||
|
|
@ -601,7 +621,7 @@ int main(int argc, char **argv)
|
|||
|
||||
Server svr;
|
||||
|
||||
svr.Get("/", [](const Request &req, Response &res)
|
||||
svr.Get("/", [](const Request &, Response &res)
|
||||
{ res.set_content("<h1>llama.cpp server works</h1>", "text/html"); });
|
||||
|
||||
svr.Post("/completion", [&llama](const Request &req, Response &res)
|
||||
|
|
@ -645,11 +665,12 @@ int main(int argc, char **argv)
|
|||
try
|
||||
{
|
||||
json data = {
|
||||
{"model", llama.params.model_alias },
|
||||
{"content", llama.generated_text },
|
||||
{"tokens_predicted", llama.num_tokens_predicted}};
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
}
|
||||
catch (json::exception e)
|
||||
catch (const json::exception &e)
|
||||
{
|
||||
// Some tokens have bad UTF-8 strings, the json parser is very sensitive
|
||||
json data = {
|
||||
|
|
@ -701,7 +722,7 @@ int main(int argc, char **argv)
|
|||
{"content", result },
|
||||
{"stop", !llama.has_next_token }};
|
||||
return res.set_content(data.dump(), "application/json");
|
||||
} catch (json::exception e) {
|
||||
} catch (const json::exception &e) {
|
||||
// Some tokens have bad UTF-8 strings, the json parser is very sensitive
|
||||
json data = {
|
||||
{"content", "" },
|
||||
|
|
|
|||
491
ggml-cuda.cu
491
ggml-cuda.cu
|
|
@ -3,6 +3,7 @@
|
|||
#include <stdint.h>
|
||||
#include <stdio.h>
|
||||
#include <atomic>
|
||||
#include <assert.h>
|
||||
|
||||
#if defined(GGML_USE_HIPBLAS)
|
||||
#include <hip/hip_runtime.h>
|
||||
|
|
@ -87,6 +88,7 @@ static_assert(sizeof(half) == sizeof(ggml_fp16_t), "wrong fp16 size");
|
|||
typedef void (*dequantize_kernel_t)(const void * vx, const int ib, const int iqs, float & v0, float & v1);
|
||||
typedef void (*to_fp32_cuda_t)(const void * x, float * y, int k, cudaStream_t stream);
|
||||
typedef void (*dequantize_mul_mat_vec_cuda_t)(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream);
|
||||
typedef void (*dot_kernel_k_t)(const void * vx, const int ib, const int iqs, const float * y, float & v);
|
||||
|
||||
// QK = number of values after dequantization
|
||||
// QR = QK / number of values before dequantization
|
||||
|
|
@ -135,6 +137,51 @@ typedef struct {
|
|||
} block_q8_0;
|
||||
static_assert(sizeof(block_q8_0) == sizeof(ggml_fp16_t) + QK8_0, "wrong q8_0 block size/padding");
|
||||
|
||||
//================================= k-quants
|
||||
|
||||
#define QK_K 256
|
||||
|
||||
typedef struct {
|
||||
uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits
|
||||
uint8_t qs[QK_K/4]; // quants
|
||||
half d; // super-block scale for quantized scales
|
||||
half dmin; // super-block scale for quantized mins
|
||||
} block_q2_k;
|
||||
static_assert(sizeof(block_q2_k) == 2*sizeof(ggml_fp16_t) + QK_K/16 + QK_K/4, "wrong q2_k block size/padding");
|
||||
|
||||
typedef struct {
|
||||
uint8_t hmask[QK_K/8];
|
||||
uint8_t qs[QK_K/4]; // nibbles / quants
|
||||
uint8_t scales[3*QK_K/64];
|
||||
half d;
|
||||
} block_q3_k;
|
||||
static_assert(sizeof(block_q3_k) == sizeof(ggml_fp16_t) + QK_K / 4 + 11 * QK_K / 64, "wrong q3_k block size/padding");
|
||||
|
||||
typedef struct {
|
||||
half d; // super-block scale for quantized scales
|
||||
half dmin; // super-block scale for quantized mins
|
||||
uint8_t scales[3*QK_K/64]; // scales, quantized with 6 bits
|
||||
uint8_t qs[QK_K/2]; // 4--bit quants
|
||||
} block_q4_k;
|
||||
static_assert(sizeof(block_q4_k) == 2*sizeof(ggml_fp16_t) + 3*QK_K/64 + QK_K/2, "wrong q4_k block size/padding");
|
||||
|
||||
typedef struct {
|
||||
half d; // super-block scale for quantized scales
|
||||
half dmin; // super-block scale for quantized mins
|
||||
uint8_t scales[3*QK_K/64]; // scales, quantized with 6 bits
|
||||
uint8_t qh[QK_K/8]; // quants, high bit
|
||||
uint8_t qs[QK_K/2]; // quants, low 4 bits
|
||||
} block_q5_k;
|
||||
static_assert(sizeof(block_q5_k) == 2*sizeof(ggml_fp16_t) + 3*QK_K/64 + QK_K/2 + QK_K/8, "wrong q5_k block size/padding");
|
||||
|
||||
typedef struct {
|
||||
uint8_t ql[QK_K/2]; // quants, lower 4 bits
|
||||
uint8_t qh[QK_K/4]; // quants, upper 2 bits
|
||||
int8_t scales[QK_K/16]; // scales
|
||||
half d; // delta
|
||||
} block_q6_k;
|
||||
static_assert(sizeof(block_q6_k) == sizeof(ggml_fp16_t) + 13*QK_K/16, "wrong q6_k block size/padding");
|
||||
|
||||
#define WARP_SIZE 32
|
||||
|
||||
#define CUDA_MUL_BLOCK_SIZE 256
|
||||
|
|
@ -236,6 +283,337 @@ static __device__ void dequantize_q8_0(const void * vx, const int ib, const int
|
|||
v1 = vi1*d;
|
||||
}
|
||||
|
||||
//================================== k-quants
|
||||
|
||||
static __global__ void dequantize_block_q2_k(const void * vx, float * yy) {
|
||||
|
||||
const int i = blockIdx.x;
|
||||
const int tid = threadIdx.x;
|
||||
const int n = tid/32;
|
||||
const int l = tid - 32*n;
|
||||
const int is = 8*n + l/16;
|
||||
|
||||
const block_q2_k * x = (const block_q2_k *) vx;
|
||||
|
||||
const uint8_t q = x[i].qs[32*n + l];
|
||||
float * y = yy + i*QK_K + 128*n;
|
||||
|
||||
float dall = x[i].d;
|
||||
float dmin = x[i].dmin;
|
||||
y[l+ 0] = dall * (x[i].scales[is+0] & 0xF) * ((q >> 0) & 3) - dmin * (x[i].scales[is+0] >> 4);
|
||||
y[l+32] = dall * (x[i].scales[is+2] & 0xF) * ((q >> 2) & 3) - dmin * (x[i].scales[is+2] >> 4);
|
||||
y[l+64] = dall * (x[i].scales[is+4] & 0xF) * ((q >> 4) & 3) - dmin * (x[i].scales[is+4] >> 4);
|
||||
y[l+96] = dall * (x[i].scales[is+6] & 0xF) * ((q >> 6) & 3) - dmin * (x[i].scales[is+6] >> 4);
|
||||
|
||||
}
|
||||
|
||||
static __device__ void vec_dot_q2_k(const void * vx, const int ib, const int iqs, const float * yy, float & result) {
|
||||
|
||||
const block_q2_k * x = (const block_q2_k *) vx;
|
||||
|
||||
// if n is 0, we want to do the lower 128, else the upper 128,
|
||||
// covering y[l+0], y[l+32], y[l+64], y[l+96] and
|
||||
// y[l+16], y[l+48], y[l+80], y[l+112]
|
||||
int n = iqs/128; // 0 or 1
|
||||
int r = iqs - 128*n; // 0...120 in steps of 8
|
||||
int l = r/8; // 0...15 in steps of 1
|
||||
|
||||
const float * y = yy + 128*n + l;
|
||||
const uint8_t * q = x[ib].qs + 32*n + l;
|
||||
const uint8_t * s = x[ib].scales + 8*n;
|
||||
|
||||
const float dall = x[ib].d;
|
||||
const float dmin = x[ib].dmin;
|
||||
|
||||
float sum = y[ 0] * (dall * ((s[0] & 0xF) * ((q[ 0] >> 0) & 3)) - dmin * (s[0] >> 4))
|
||||
+ y[ 32] * (dall * ((s[2] & 0xF) * ((q[ 0] >> 2) & 3)) - dmin * (s[2] >> 4))
|
||||
+ y[ 64] * (dall * ((s[4] & 0xF) * ((q[ 0] >> 4) & 3)) - dmin * (s[4] >> 4))
|
||||
+ y[ 96] * (dall * ((s[6] & 0xF) * ((q[ 0] >> 6) & 3)) - dmin * (s[6] >> 4))
|
||||
+ y[ 16] * (dall * ((s[1] & 0xF) * ((q[16] >> 0) & 3)) - dmin * (s[1] >> 4))
|
||||
+ y[ 48] * (dall * ((s[3] & 0xF) * ((q[16] >> 2) & 3)) - dmin * (s[3] >> 4))
|
||||
+ y[ 80] * (dall * ((s[5] & 0xF) * ((q[16] >> 4) & 3)) - dmin * (s[5] >> 4))
|
||||
+ y[112] * (dall * ((s[7] & 0xF) * ((q[16] >> 6) & 3)) - dmin * (s[7] >> 4));
|
||||
|
||||
result = sum;
|
||||
|
||||
}
|
||||
|
||||
static __global__ void dequantize_block_q3_k(const void * vx, float * yy) {
|
||||
|
||||
int r = threadIdx.x/4;
|
||||
int i = blockIdx.x;
|
||||
int tid = r/2;
|
||||
int is0 = r%2;
|
||||
int l0 = 16*is0 + 4*(threadIdx.x%4);
|
||||
int n = tid / 4;
|
||||
int j = tid - 4*n;
|
||||
|
||||
const block_q3_k * x = (const block_q3_k *) vx;
|
||||
|
||||
uint8_t m = 1 << (4*n + j);
|
||||
int is = 8*n + 2*j + is0;
|
||||
int shift = 2*j;
|
||||
|
||||
int8_t us = is < 4 ? (x[i].scales[is-0] & 0xF) | (((x[i].scales[is+8] >> 0) & 3) << 4) :
|
||||
is < 8 ? (x[i].scales[is-0] & 0xF) | (((x[i].scales[is+4] >> 2) & 3) << 4) :
|
||||
is < 12 ? (x[i].scales[is-8] >> 4) | (((x[i].scales[is+0] >> 4) & 3) << 4) :
|
||||
(x[i].scales[is-8] >> 4) | (((x[i].scales[is-4] >> 6) & 3) << 4);
|
||||
float d_all = x[i].d;
|
||||
float dl = d_all * (us - 32);
|
||||
|
||||
float * y = yy + i*QK_K + 128*n + 32*j;
|
||||
const uint8_t * q = x[i].qs + 32*n;
|
||||
const uint8_t * hm = x[i].hmask;
|
||||
|
||||
for (int l = l0; l < l0+4; ++l) y[l] = dl * ((int8_t)((q[l] >> shift) & 3) - ((hm[l] & m) ? 0 : 4));
|
||||
|
||||
}
|
||||
|
||||
static __device__ void vec_dot_q3_k(const void * vx, const int ib, const int iqs, const float * yy, float & result) {
|
||||
|
||||
const block_q3_k * x = (const block_q3_k *) vx;
|
||||
|
||||
const uint32_t kmask1 = 0x03030303;
|
||||
const uint32_t kmask2 = 0x0f0f0f0f;
|
||||
|
||||
uint32_t aux[3];
|
||||
uint32_t utmp[4];
|
||||
|
||||
// if n is 0, we want to do the lower 128, else the upper 128,
|
||||
// covering y[l+0], y[l+32], y[l+64], y[l+96] and
|
||||
// y[l+16], y[l+48], y[l+80], y[l+112]
|
||||
int n = iqs/128; // 0 or 1
|
||||
int r = iqs - 128*n; // 0...120 in steps of 8
|
||||
int l = r/8; // 0...15 in steps of 1
|
||||
|
||||
const float * y = yy + 128*n + l;
|
||||
const uint8_t * q = x[ib].qs + 32*n + l;
|
||||
const uint8_t * hm = x[ib].hmask + l;
|
||||
const int8_t * s = (const int8_t *)utmp + 8*n;
|
||||
|
||||
memcpy(aux, x[ib].scales, 12);
|
||||
utmp[3] = ((aux[1] >> 4) & kmask2) | (((aux[2] >> 6) & kmask1) << 4);
|
||||
utmp[2] = ((aux[0] >> 4) & kmask2) | (((aux[2] >> 4) & kmask1) << 4);
|
||||
utmp[1] = (aux[1] & kmask2) | (((aux[2] >> 2) & kmask1) << 4);
|
||||
utmp[0] = (aux[0] & kmask2) | (((aux[2] >> 0) & kmask1) << 4);
|
||||
|
||||
const float dall = x[ib].d;
|
||||
|
||||
const uint8_t m = 1 << (4*n);
|
||||
|
||||
float sum = y[ 0] * (s[0] - 32) * (((q[ 0] >> 0) & 3) - (hm[ 0] & (m << 0) ? 0 : 4))
|
||||
+ y[ 32] * (s[2] - 32) * (((q[ 0] >> 2) & 3) - (hm[ 0] & (m << 1) ? 0 : 4))
|
||||
+ y[ 64] * (s[4] - 32) * (((q[ 0] >> 4) & 3) - (hm[ 0] & (m << 2) ? 0 : 4))
|
||||
+ y[ 96] * (s[6] - 32) * (((q[ 0] >> 6) & 3) - (hm[ 0] & (m << 3) ? 0 : 4))
|
||||
+ y[ 16] * (s[1] - 32) * (((q[16] >> 0) & 3) - (hm[16] & (m << 0) ? 0 : 4))
|
||||
+ y[ 48] * (s[3] - 32) * (((q[16] >> 2) & 3) - (hm[16] & (m << 1) ? 0 : 4))
|
||||
+ y[ 80] * (s[5] - 32) * (((q[16] >> 4) & 3) - (hm[16] & (m << 2) ? 0 : 4))
|
||||
+ y[112] * (s[7] - 32) * (((q[16] >> 6) & 3) - (hm[16] & (m << 3) ? 0 : 4));
|
||||
|
||||
result = sum * dall;
|
||||
|
||||
}
|
||||
|
||||
static inline __device__ void get_scale_min_k4(int j, const uint8_t * q, uint8_t & d, uint8_t & m) {
|
||||
if (j < 4) {
|
||||
d = q[j] & 63; m = q[j + 4] & 63;
|
||||
} else {
|
||||
d = (q[j+4] & 0xF) | ((q[j-4] >> 6) << 4);
|
||||
m = (q[j+4] >> 4) | ((q[j-0] >> 6) << 4);
|
||||
}
|
||||
}
|
||||
|
||||
static __global__ void dequantize_block_q4_k(const void * vx, float * yy) {
|
||||
const block_q4_k * x = (const block_q4_k *) vx;
|
||||
|
||||
const int i = blockIdx.x;
|
||||
|
||||
//// assume 64 threads - this is very slightly better than the one below
|
||||
//const int tid = threadIdx.x;
|
||||
//const int il = tid/16;
|
||||
//const int ir = tid%16;
|
||||
//const int is = 2*il;
|
||||
//const int n = 2;
|
||||
|
||||
// assume 32 threads
|
||||
const int tid = threadIdx.x;
|
||||
const int il = tid/8;
|
||||
const int ir = tid%8;
|
||||
const int is = 2*il;
|
||||
const int n = 4;
|
||||
|
||||
float * y = yy + i*QK_K + 64*il + n*ir;
|
||||
|
||||
const float dall = x[i].d;
|
||||
const float dmin = x[i].dmin;
|
||||
|
||||
const uint8_t * q = x[i].qs + 32*il + n*ir;
|
||||
|
||||
uint8_t sc, m;
|
||||
get_scale_min_k4(is + 0, x[i].scales, sc, m);
|
||||
const float d1 = dall * sc; const float m1 = dmin * m;
|
||||
get_scale_min_k4(is + 1, x[i].scales, sc, m);
|
||||
const float d2 = dall * sc; const float m2 = dmin * m;
|
||||
for (int l = 0; l < n; ++l) {
|
||||
y[l + 0] = d1 * (q[l] & 0xF) - m1;
|
||||
y[l +32] = d2 * (q[l] >> 4) - m2;
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ void vec_dot_q4_k(const void * vx, const int ib, const int iqs, const float * yy, float & result) {
|
||||
|
||||
const block_q4_k * x = (const block_q4_k *) vx;
|
||||
|
||||
// iqs is in 0...248 in steps of 8 =>
|
||||
const int j = iqs / 64; // j is in 0...3
|
||||
const int ir = (iqs - 64*j)/2; // ir is in 0...28 in steps of 4
|
||||
const int is = 2*j; // is is in 0...6 in steps of 2
|
||||
|
||||
const float * y = yy + 64*j + ir;
|
||||
const uint8_t * q = x[ib].qs + 32*j + ir;
|
||||
|
||||
const float dall = x[ib].d;
|
||||
const float dmin = x[ib].dmin;
|
||||
|
||||
uint8_t sc, m;
|
||||
get_scale_min_k4(is + 0, x[ib].scales, sc, m);
|
||||
const float d1 = dall * sc;
|
||||
const float m1 = dmin * m;
|
||||
get_scale_min_k4(is + 1, x[ib].scales, sc, m);
|
||||
const float d2 = dall * sc;
|
||||
const float m2 = dmin * m;
|
||||
|
||||
float sum = 0;
|
||||
for (int k = 0; k < 4; ++k) {
|
||||
sum += y[k + 0] * (d1 * (q[k] & 0xF) - m1);
|
||||
sum += y[k + 32] * (d2 * (q[k] >> 4) - m2);
|
||||
}
|
||||
result = sum;
|
||||
|
||||
}
|
||||
|
||||
static __global__ void dequantize_block_q5_k(const void * vx, float * yy) {
|
||||
const block_q5_k * x = (const block_q5_k *) vx;
|
||||
|
||||
const int i = blockIdx.x;
|
||||
|
||||
// assume 64 threads - this is very slightly better than the one below
|
||||
const int tid = threadIdx.x;
|
||||
const int il = tid/16; // il is in 0...3
|
||||
const int ir = tid%16; // ir is in 0...15
|
||||
const int is = 2*il; // is is in 0...6
|
||||
|
||||
float * y = yy + i*QK_K + 64*il + 2*ir;
|
||||
|
||||
const float dall = x[i].d;
|
||||
const float dmin = x[i].dmin;
|
||||
|
||||
const uint8_t * ql = x[i].qs + 32*il + 2*ir;
|
||||
const uint8_t * qh = x[i].qh + 2*ir;
|
||||
|
||||
uint8_t sc, m;
|
||||
get_scale_min_k4(is + 0, x[i].scales, sc, m);
|
||||
const float d1 = dall * sc; const float m1 = dmin * m;
|
||||
get_scale_min_k4(is + 1, x[i].scales, sc, m);
|
||||
const float d2 = dall * sc; const float m2 = dmin * m;
|
||||
|
||||
uint8_t hm = 1 << (2*il);
|
||||
y[ 0] = d1 * ((ql[ 0] & 0xF) + (qh[ 0] & hm ? 16 : 0)) - m1;
|
||||
y[ 1] = d1 * ((ql[ 1] & 0xF) + (qh[ 1] & hm ? 16 : 0)) - m1;
|
||||
hm <<= 1;
|
||||
y[32] = d2 * ((ql[ 0] >> 4) + (qh[ 0] & hm ? 16 : 0)) - m2;
|
||||
y[33] = d2 * ((ql[ 1] >> 4) + (qh[ 1] & hm ? 16 : 0)) - m2;
|
||||
}
|
||||
|
||||
static __device__ void vec_dot_q5_k(const void * vx, const int ib, const int iqs, const float * yy, float & result) {
|
||||
|
||||
const block_q5_k * x = (const block_q5_k *) vx;
|
||||
|
||||
// iqs is in 0...248 in steps of 8 =>
|
||||
const int j = iqs / 64; // j is in 0...3
|
||||
const int ir = (iqs - 64*j)/2; // ir is in 0...28 in steps of 4
|
||||
const int is = 2*j; // is is in 0...6 in steps of 2
|
||||
|
||||
const float * y = yy + 64*j + ir;
|
||||
const uint8_t * ql = x[ib].qs + 32*j + ir;
|
||||
const uint8_t * qh = x[ib].qh + ir;
|
||||
|
||||
const float dall = x[ib].d;
|
||||
const float dmin = x[ib].dmin;
|
||||
|
||||
uint8_t sc, m;
|
||||
get_scale_min_k4(is + 0, x[ib].scales, sc, m);
|
||||
const float d1 = dall * sc;
|
||||
const float m1 = dmin * m;
|
||||
get_scale_min_k4(is + 1, x[ib].scales, sc, m);
|
||||
const float d2 = dall * sc;
|
||||
const float m2 = dmin * m;
|
||||
|
||||
uint8_t hm = 1 << is;
|
||||
float sum = 0;
|
||||
for (int k = 0; k < 4; ++k) {
|
||||
sum += y[k + 0] * (d1 * ((ql[k] & 0xF) + (qh[k] & hm ? 16 : 0)) - m1);
|
||||
}
|
||||
hm <<= 1;
|
||||
for (int k = 0; k < 4; ++k) {
|
||||
sum += y[k + 32] * (d2 * ((ql[k] >> 4) + (qh[k] & hm ? 16 : 0)) - m2);
|
||||
}
|
||||
result = sum;
|
||||
|
||||
}
|
||||
|
||||
static __global__ void dequantize_block_q6_k(const void * vx, float * yy) {
|
||||
const block_q6_k * x = (const block_q6_k *) vx;
|
||||
|
||||
const int i = blockIdx.x;
|
||||
|
||||
// assume 64 threads - this is very slightly better than the one below
|
||||
const int tid = threadIdx.x;
|
||||
const int ip = tid/32; // ip is 0 or 1
|
||||
const int il = tid - 32*ip; // 0...32
|
||||
const int is = 8*ip + il/16;
|
||||
|
||||
float * y = yy + i*QK_K + 128*ip + il;
|
||||
|
||||
const float d = x[i].d;
|
||||
|
||||
const uint8_t * ql = x[i].ql + 64*ip + il;
|
||||
const uint8_t qh = x[i].qh[32*ip + il];
|
||||
const int8_t * sc = x[i].scales + is;
|
||||
|
||||
y[ 0] = d * sc[0] * ((int8_t)((ql[ 0] & 0xF) | (((qh >> 0) & 3) << 4)) - 32);
|
||||
y[32] = d * sc[2] * ((int8_t)((ql[32] & 0xF) | (((qh >> 2) & 3) << 4)) - 32);
|
||||
y[64] = d * sc[4] * ((int8_t)((ql[ 0] >> 4) | (((qh >> 4) & 3) << 4)) - 32);
|
||||
y[96] = d * sc[6] * ((int8_t)((ql[32] >> 4) | (((qh >> 6) & 3) << 4)) - 32);
|
||||
}
|
||||
|
||||
static __device__ void vec_dot_q6_k(const void * vx, const int ib, const int iqs, const float * yy, float & result) {
|
||||
|
||||
const block_q6_k * x = (const block_q6_k *) vx;
|
||||
|
||||
const int ip = iqs / 128; // 0 or 1
|
||||
const int il = (iqs - 128*ip)/8; // 0...15
|
||||
const int is = 8*ip;
|
||||
|
||||
const float * y = yy + 128*ip + il;
|
||||
|
||||
const float d = x[ib].d;
|
||||
|
||||
const uint8_t * ql = x[ib].ql + 64*ip + il;
|
||||
const uint8_t * qh = x[ib].qh + 32*ip + il;
|
||||
const int8_t * sc = x[ib].scales + is;
|
||||
|
||||
result = y[ 0] * d * sc[0] * ((int8_t)((ql[ 0] & 0xF) | (((qh[ 0] >> 0) & 3) << 4)) - 32)
|
||||
+ y[ 32] * d * sc[2] * ((int8_t)((ql[32] & 0xF) | (((qh[ 0] >> 2) & 3) << 4)) - 32)
|
||||
+ y[ 64] * d * sc[4] * ((int8_t)((ql[ 0] >> 4) | (((qh[ 0] >> 4) & 3) << 4)) - 32)
|
||||
+ y[ 96] * d * sc[6] * ((int8_t)((ql[32] >> 4) | (((qh[ 0] >> 6) & 3) << 4)) - 32)
|
||||
+ y[ 16] * d * sc[1] * ((int8_t)((ql[16] & 0xF) | (((qh[16] >> 0) & 3) << 4)) - 32)
|
||||
+ y[ 48] * d * sc[3] * ((int8_t)((ql[48] & 0xF) | (((qh[16] >> 2) & 3) << 4)) - 32)
|
||||
+ y[ 80] * d * sc[5] * ((int8_t)((ql[16] >> 4) | (((qh[16] >> 4) & 3) << 4)) - 32)
|
||||
+ y[112] * d * sc[7] * ((int8_t)((ql[48] >> 4) | (((qh[16] >> 6) & 3) << 4)) - 32);
|
||||
|
||||
}
|
||||
|
||||
static __device__ void convert_f16(const void * vx, const int ib, const int iqs, float & v0, float & v1){
|
||||
const half * x = (const half *) vx;
|
||||
|
||||
|
|
@ -310,6 +688,41 @@ static __global__ void dequantize_mul_mat_vec(const void * vx, const float * y,
|
|||
}
|
||||
}
|
||||
|
||||
template <int n_thread, dot_kernel_k_t dot_kernel>
|
||||
static __global__ void dequantize_mul_mat_vec_k(const void * vx, const float * y, float * dst, const int ncols) {
|
||||
const int row = blockIdx.x*blockDim.y + threadIdx.y;
|
||||
const int tid = threadIdx.x;
|
||||
|
||||
const int iter_stride = QK_K;
|
||||
const int vals_per_iter = iter_stride / n_thread;
|
||||
const int num_blocks_per_row = ncols / QK_K;
|
||||
const int ib0 = row*num_blocks_per_row;
|
||||
|
||||
float tmp = 0; // partial sum for thread in warp
|
||||
|
||||
for (int i = 0; i < ncols; i += iter_stride) {
|
||||
const int col = i + vals_per_iter*tid;
|
||||
const int ib = ib0 + col/QK_K; // x block index
|
||||
const int iqs = col%QK_K; // x quant index
|
||||
const int iybs = col - col%QK_K; // y block start index
|
||||
|
||||
float v;
|
||||
dot_kernel(vx, ib, iqs, y + iybs, v);
|
||||
tmp += v;
|
||||
}
|
||||
|
||||
// sum up partial sums and write back result
|
||||
__syncthreads();
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
|
||||
if (tid == 0) {
|
||||
dst[row] = tmp;
|
||||
}
|
||||
}
|
||||
|
||||
static void mul_f32_cuda(const float * x, const float * y, float * dst, const int kx, const int ky, cudaStream_t stream) {
|
||||
const int num_blocks = (kx + CUDA_MUL_BLOCK_SIZE - 1) / CUDA_MUL_BLOCK_SIZE;
|
||||
mul_f32<<<num_blocks, CUDA_MUL_BLOCK_SIZE, 0, stream>>>(x, y, dst, kx, ky);
|
||||
|
|
@ -340,6 +753,31 @@ static void dequantize_row_q8_0_cuda(const void * vx, float * y, const int k, cu
|
|||
dequantize_block<QK8_0, QR8_0, dequantize_q8_0><<<num_blocks, CUDA_DEQUANTIZE_BLOCK_SIZE, 0, stream>>>(vx, y, k);
|
||||
}
|
||||
|
||||
static void dequantize_row_q2_k_cuda(const void * vx, float * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_q2_k<<<nb, 64, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
static void dequantize_row_q3_k_cuda(const void * vx, float * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_q3_k<<<nb, 64, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
static void dequantize_row_q4_k_cuda(const void * vx, float * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_q4_k<<<nb, 32, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
static void dequantize_row_q5_k_cuda(const void * vx, float * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_q5_k<<<nb, 64, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
static void dequantize_row_q6_k_cuda(const void * vx, float * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_q6_k<<<nb, 64, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
static void dequantize_mul_mat_vec_q4_0_cuda(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % GGML_CUDA_DMMV_X == 0);
|
||||
GGML_ASSERT(nrows % GGML_CUDA_DMMV_Y == 0);
|
||||
|
|
@ -380,6 +818,37 @@ static void dequantize_mul_mat_vec_q8_0_cuda(const void * vx, const float * y, f
|
|||
<<<nrows/GGML_CUDA_DMMV_Y, block_dims, 0, stream>>>(vx, y, dst, ncols);
|
||||
}
|
||||
|
||||
static void dequantize_mul_mat_vec_q2_k_cuda(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % QK_K == 0);
|
||||
const int ny = 2;
|
||||
const dim3 block_dims(32, ny, 1);
|
||||
dequantize_mul_mat_vec_k<32, vec_dot_q2_k><<<(nrows + ny - 1)/ny, block_dims, 0, stream>>>(vx, y, dst, ncols);
|
||||
}
|
||||
|
||||
static void dequantize_mul_mat_vec_q3_k_cuda(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % QK_K == 0);
|
||||
const dim3 block_dims(32, 2, 1);
|
||||
dequantize_mul_mat_vec_k<32, vec_dot_q3_k><<<nrows/2, block_dims, 0, stream>>>(vx, y, dst, ncols);
|
||||
}
|
||||
|
||||
static void dequantize_mul_mat_vec_q4_k_cuda(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % QK_K == 0);
|
||||
const dim3 block_dims(32, 2, 1);
|
||||
dequantize_mul_mat_vec_k<32, vec_dot_q4_k><<<nrows/2, block_dims, 0, stream>>>(vx, y, dst, ncols);
|
||||
}
|
||||
|
||||
static void dequantize_mul_mat_vec_q5_k_cuda(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % QK_K == 0);
|
||||
const dim3 block_dims(32, 2, 1);
|
||||
dequantize_mul_mat_vec_k<32, vec_dot_q5_k><<<nrows/2, block_dims, 0, stream>>>(vx, y, dst, ncols);
|
||||
}
|
||||
|
||||
static void dequantize_mul_mat_vec_q6_k_cuda(const void * vx, const float * y, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % QK_K == 0);
|
||||
const dim3 block_dims(32, 2, 1);
|
||||
dequantize_mul_mat_vec_k<32, vec_dot_q6_k><<<nrows/2, block_dims, 0, stream>>>(vx, y, dst, ncols);
|
||||
}
|
||||
|
||||
static void convert_fp16_to_fp32_cuda(const void * vx, float * y, const int k, cudaStream_t stream) {
|
||||
const int num_blocks = (k + CUDA_DEQUANTIZE_BLOCK_SIZE - 1) / CUDA_DEQUANTIZE_BLOCK_SIZE;
|
||||
dequantize_block<32, 1, convert_f16><<<num_blocks, CUDA_DEQUANTIZE_BLOCK_SIZE, 0, stream>>>(vx, y, k);
|
||||
|
|
@ -405,6 +874,16 @@ static to_fp32_cuda_t ggml_get_to_fp32_cuda(ggml_type type) {
|
|||
return dequantize_row_q5_1_cuda;
|
||||
case GGML_TYPE_Q8_0:
|
||||
return dequantize_row_q8_0_cuda;
|
||||
case GGML_TYPE_Q2_K:
|
||||
return dequantize_row_q2_k_cuda;
|
||||
case GGML_TYPE_Q3_K:
|
||||
return dequantize_row_q3_k_cuda;
|
||||
case GGML_TYPE_Q4_K:
|
||||
return dequantize_row_q4_k_cuda;
|
||||
case GGML_TYPE_Q5_K:
|
||||
return dequantize_row_q5_k_cuda;
|
||||
case GGML_TYPE_Q6_K:
|
||||
return dequantize_row_q6_k_cuda;
|
||||
case GGML_TYPE_F16:
|
||||
return convert_fp16_to_fp32_cuda;
|
||||
default:
|
||||
|
|
@ -424,6 +903,16 @@ static dequantize_mul_mat_vec_cuda_t ggml_get_dequantize_mul_mat_vec_cuda(ggml_t
|
|||
return dequantize_mul_mat_vec_q5_1_cuda;
|
||||
case GGML_TYPE_Q8_0:
|
||||
return dequantize_mul_mat_vec_q8_0_cuda;
|
||||
case GGML_TYPE_Q2_K:
|
||||
return dequantize_mul_mat_vec_q2_k_cuda;
|
||||
case GGML_TYPE_Q3_K:
|
||||
return dequantize_mul_mat_vec_q3_k_cuda;
|
||||
case GGML_TYPE_Q4_K:
|
||||
return dequantize_mul_mat_vec_q4_k_cuda;
|
||||
case GGML_TYPE_Q5_K:
|
||||
return dequantize_mul_mat_vec_q5_k_cuda;
|
||||
case GGML_TYPE_Q6_K:
|
||||
return dequantize_mul_mat_vec_q6_k_cuda;
|
||||
case GGML_TYPE_F16:
|
||||
return convert_mul_mat_vec_f16_cuda;
|
||||
default:
|
||||
|
|
@ -842,12 +1331,14 @@ static void ggml_cuda_mul_mat_q_f32(const ggml_tensor * src0, const ggml_tensor
|
|||
CUDA_CHECK(cudaStreamWaitEvent(cudaStream, cudaEvent, 0));
|
||||
|
||||
// compute
|
||||
//printf("Calling dmmv\n");
|
||||
dmmv(c_Q, c_Y, c_D, ne00, ne01, cudaStream);
|
||||
CUDA_CHECK(cudaGetLastError());
|
||||
|
||||
} else { // general dequantization kernel + cuBLAS matrix matrix multiplication
|
||||
float * c_X = d_X + i * x_ne;
|
||||
|
||||
//typedef void (*to_fp32_cuda_t)(const void * x, float * y, int k, cudaStream_t stream);
|
||||
// convert src0 to fp32 on device
|
||||
to_fp32_cuda(c_Q, c_X, x_ne, cudaStream2);
|
||||
CUDA_CHECK(cudaGetLastError());
|
||||
|
|
|
|||
63
ggml-metal.h
Normal file
63
ggml-metal.h
Normal file
|
|
@ -0,0 +1,63 @@
|
|||
// An interface allowing to compute ggml_cgraph with Metal
|
||||
//
|
||||
// This is a fully functional interface that extends ggml with GPU support for Apple devices.
|
||||
// A similar interface can be created for other GPU backends (e.g. Vulkan, CUDA, OpenCL, etc.)
|
||||
//
|
||||
// How it works?
|
||||
//
|
||||
// As long as your program can create and evaluate a ggml_cgraph on the CPU, you can use this
|
||||
// interface to evaluate the same graph on the GPU. Instead of using ggml_graph_compute(), you
|
||||
// use ggml_metal_graph_compute() (or ggml_vulkan_graph_compute(), etc.)
|
||||
//
|
||||
// You only need to make sure that all memory buffers that you used during the graph creation
|
||||
// are mapped to the device memory with the ggml_metal_add_buffer() function. This mapping is
|
||||
// used during the graph evaluation to determine the arguments of the compute kernels.
|
||||
//
|
||||
// Synchronization between device and host memory (for example for input and output tensors)
|
||||
// is done with the ggml_metal_set_tensor() and ggml_metal_get_tensor() functions.
|
||||
//
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <stddef.h>
|
||||
#include <stdbool.h>
|
||||
|
||||
// max memory buffers that can be mapped to the device
|
||||
#define GGML_METAL_MAX_BUFFERS 16
|
||||
|
||||
struct ggml_tensor;
|
||||
struct ggml_cgraph;
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
struct ggml_metal_context;
|
||||
|
||||
struct ggml_metal_context * ggml_metal_init(void);
|
||||
void ggml_metal_free(struct ggml_metal_context * ctx);
|
||||
|
||||
// creates a mapping between a host memory buffer and a device memory buffer
|
||||
// - make sure to map all buffers used in the graph before calling ggml_metal_graph_compute
|
||||
// - the mapping is used during computation to determine the arguments of the compute kernels
|
||||
// - you don't need to keep the host memory buffer allocated as it is never accessed by Metal
|
||||
//
|
||||
bool ggml_metal_add_buffer(
|
||||
struct ggml_metal_context * ctx,
|
||||
const char * name,
|
||||
void * data,
|
||||
size_t size);
|
||||
|
||||
// set data from host memory into the device
|
||||
void ggml_metal_set_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
|
||||
|
||||
// get data from the device into host memory
|
||||
void ggml_metal_get_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
|
||||
|
||||
// same as ggml_graph_compute but uses Metal
|
||||
void ggml_metal_graph_compute(struct ggml_metal_context * ctx, struct ggml_cgraph * gf);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
688
ggml-metal.m
Normal file
688
ggml-metal.m
Normal file
|
|
@ -0,0 +1,688 @@
|
|||
#import "ggml-metal.h"
|
||||
|
||||
#import "ggml.h"
|
||||
|
||||
#import <Foundation/Foundation.h>
|
||||
|
||||
#import <Metal/Metal.h>
|
||||
#import <MetalPerformanceShaders/MetalPerformanceShaders.h>
|
||||
|
||||
#ifdef GGML_METAL_NDEBUG
|
||||
#define metal_printf(...)
|
||||
#else
|
||||
#define metal_printf(...) fprintf(stderr, __VA_ARGS__)
|
||||
#endif
|
||||
|
||||
#define UNUSED(x) (void)(x)
|
||||
|
||||
struct ggml_metal_buffer {
|
||||
const char * name;
|
||||
|
||||
void * data;
|
||||
size_t size;
|
||||
|
||||
id<MTLBuffer> metal;
|
||||
};
|
||||
|
||||
struct ggml_metal_context {
|
||||
float * logits;
|
||||
|
||||
id<MTLDevice> device;
|
||||
id<MTLCommandQueue> queue;
|
||||
id<MTLLibrary> library;
|
||||
|
||||
int n_buffers;
|
||||
struct ggml_metal_buffer buffers[GGML_METAL_MAX_BUFFERS];
|
||||
|
||||
// custom kernels
|
||||
#define GGML_METAL_DECL_KERNEL(name) \
|
||||
id<MTLFunction> function_##name; \
|
||||
id<MTLComputePipelineState> pipeline_##name
|
||||
|
||||
GGML_METAL_DECL_KERNEL(add);
|
||||
GGML_METAL_DECL_KERNEL(mul);
|
||||
GGML_METAL_DECL_KERNEL(mul_row); // TODO: avoid this extra kernel, instead extend the "mul" kernel to support broadcast
|
||||
GGML_METAL_DECL_KERNEL(scale);
|
||||
GGML_METAL_DECL_KERNEL(silu);
|
||||
GGML_METAL_DECL_KERNEL(relu);
|
||||
GGML_METAL_DECL_KERNEL(soft_max);
|
||||
GGML_METAL_DECL_KERNEL(diag_mask_inf);
|
||||
GGML_METAL_DECL_KERNEL(get_rows_q4_0);
|
||||
GGML_METAL_DECL_KERNEL(rms_norm);
|
||||
GGML_METAL_DECL_KERNEL(mul_mat_q4_0_f32);
|
||||
GGML_METAL_DECL_KERNEL(mul_mat_f16_f32);
|
||||
GGML_METAL_DECL_KERNEL(rope);
|
||||
GGML_METAL_DECL_KERNEL(cpy_f32_f16);
|
||||
GGML_METAL_DECL_KERNEL(cpy_f32_f32);
|
||||
|
||||
#undef GGML_METAL_DECL_KERNEL
|
||||
};
|
||||
|
||||
// MSL code
|
||||
// TODO: move the contents here when ready
|
||||
// for now it is easier to work in a separate file
|
||||
static NSString * const msl_library_source = @"see metal.metal";
|
||||
|
||||
struct ggml_metal_context * ggml_metal_init(void) {
|
||||
fprintf(stderr, "%s: allocating\n", __func__);
|
||||
|
||||
struct ggml_metal_context * ctx = malloc(sizeof(struct ggml_metal_context));
|
||||
|
||||
ctx->device = MTLCreateSystemDefaultDevice();
|
||||
ctx->queue = [ctx->device newCommandQueue];
|
||||
|
||||
// determine if we can use MPS
|
||||
if (MPSSupportsMTLDevice(ctx->device)) {
|
||||
fprintf(stderr, "%s: using MPS\n", __func__);
|
||||
} else {
|
||||
fprintf(stderr, "%s: not using MPS\n", __func__);
|
||||
GGML_ASSERT(false && "MPS not supported");
|
||||
}
|
||||
|
||||
#if 0
|
||||
// compile from source string and show compile log
|
||||
{
|
||||
NSError * error = nil;
|
||||
|
||||
ctx->library = [ctx->device newLibraryWithSource:msl_library_source options:nil error:&error];
|
||||
if (error) {
|
||||
fprintf(stderr, "%s: error: %s\n", __func__, [[error description] UTF8String]);
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
#else
|
||||
UNUSED(msl_library_source);
|
||||
|
||||
// read the source from "ggml-metal.metal" into a string and use newLibraryWithSource
|
||||
{
|
||||
NSError * error = nil;
|
||||
|
||||
//NSString * path = [[NSBundle mainBundle] pathForResource:@"../../examples/metal/metal" ofType:@"metal"];
|
||||
NSString * path = [[NSBundle mainBundle] pathForResource:@"ggml-metal" ofType:@"metal"];
|
||||
fprintf(stderr, "%s: loading '%s'\n", __func__, [path UTF8String]);
|
||||
|
||||
NSString * src = [NSString stringWithContentsOfFile:path encoding:NSUTF8StringEncoding error:&error];
|
||||
if (error) {
|
||||
fprintf(stderr, "%s: error: %s\n", __func__, [[error description] UTF8String]);
|
||||
exit(1);
|
||||
}
|
||||
|
||||
ctx->library = [ctx->device newLibraryWithSource:src options:nil error:&error];
|
||||
if (error) {
|
||||
fprintf(stderr, "%s: error: %s\n", __func__, [[error description] UTF8String]);
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
// load kernels
|
||||
{
|
||||
#define GGML_METAL_ADD_KERNEL(name) \
|
||||
ctx->function_##name = [ctx->library newFunctionWithName:@"kernel_"#name]; \
|
||||
ctx->pipeline_##name = [ctx->device newComputePipelineStateWithFunction:ctx->function_##name error:nil]; \
|
||||
fprintf(stderr, "%s: loaded %-32s %16p\n", __func__, "kernel_"#name, (void *) ctx->pipeline_##name);
|
||||
|
||||
GGML_METAL_ADD_KERNEL(add);
|
||||
GGML_METAL_ADD_KERNEL(mul);
|
||||
GGML_METAL_ADD_KERNEL(mul_row);
|
||||
GGML_METAL_ADD_KERNEL(scale);
|
||||
GGML_METAL_ADD_KERNEL(silu);
|
||||
GGML_METAL_ADD_KERNEL(relu);
|
||||
GGML_METAL_ADD_KERNEL(soft_max);
|
||||
GGML_METAL_ADD_KERNEL(diag_mask_inf);
|
||||
GGML_METAL_ADD_KERNEL(get_rows_q4_0);
|
||||
GGML_METAL_ADD_KERNEL(rms_norm);
|
||||
GGML_METAL_ADD_KERNEL(mul_mat_q4_0_f32);
|
||||
GGML_METAL_ADD_KERNEL(mul_mat_f16_f32);
|
||||
GGML_METAL_ADD_KERNEL(rope);
|
||||
GGML_METAL_ADD_KERNEL(cpy_f32_f16);
|
||||
GGML_METAL_ADD_KERNEL(cpy_f32_f32);
|
||||
|
||||
#undef GGML_METAL_ADD_KERNEL
|
||||
}
|
||||
|
||||
return ctx;
|
||||
}
|
||||
|
||||
void ggml_metal_free(struct ggml_metal_context * ctx) {
|
||||
fprintf(stderr, "%s: deallocating\n", __func__);
|
||||
|
||||
free(ctx);
|
||||
}
|
||||
|
||||
// finds the Metal buffer that contains the tensor data on the GPU device
|
||||
// the assumption is that there is 1-to-1 mapping between the host and device memory buffers, so we can find the
|
||||
// Metal buffer based on the host memory pointer
|
||||
//
|
||||
static id<MTLBuffer> ggml_metal_get_buffer(struct ggml_metal_context * ctx, struct ggml_tensor * t, size_t * offs) {
|
||||
//fprintf(stderr, "%s: data tensor '%16s', offs_data = %8ld, offs_eval = %8ld, offs_cach = %8ld\n", __func__, t->name, offs_data, offs_eval, offs_cach);
|
||||
|
||||
for (int i = 0; i < ctx->n_buffers; ++i) {
|
||||
const int64_t ioffs = (int64_t) t->data - (int64_t) ctx->buffers[i].data;
|
||||
|
||||
if (ioffs >= 0 && ioffs < (int64_t) ctx->buffers[i].size) {
|
||||
*offs = (size_t) ioffs;
|
||||
|
||||
//fprintf(stderr, "%s: '%s' tensor '%16s', offs = %8ld\n", __func__, ctx->buffers[i].name, t->name, *offs);
|
||||
|
||||
return ctx->buffers[i].metal;
|
||||
}
|
||||
}
|
||||
|
||||
fprintf(stderr, "%s: error: buffer is nil\n", __func__);
|
||||
|
||||
return nil;
|
||||
}
|
||||
|
||||
bool ggml_metal_add_buffer(
|
||||
struct ggml_metal_context * ctx,
|
||||
const char * name,
|
||||
void * data,
|
||||
size_t size) {
|
||||
if (ctx->n_buffers >= GGML_METAL_MAX_BUFFERS) {
|
||||
fprintf(stderr, "%s: too many buffers\n", __func__);
|
||||
return false;
|
||||
}
|
||||
|
||||
if (data) {
|
||||
// verify that the buffer does not overlap with any of the existing buffers
|
||||
for (int i = 0; i < ctx->n_buffers; ++i) {
|
||||
const int64_t ioffs = (int64_t) data - (int64_t) ctx->buffers[i].data;
|
||||
|
||||
if (ioffs >= 0 && ioffs < (int64_t) ctx->buffers[i].size) {
|
||||
fprintf(stderr, "%s: error: buffer '%s' overlaps with '%s'\n", __func__, name, ctx->buffers[i].name);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
size_t page_size = getpagesize();
|
||||
size_t aligned_size = size;
|
||||
if ((aligned_size % page_size) != 0) {
|
||||
aligned_size += (page_size - (aligned_size % page_size));
|
||||
}
|
||||
|
||||
ctx->buffers[ctx->n_buffers].name = name;
|
||||
ctx->buffers[ctx->n_buffers].data = data;
|
||||
ctx->buffers[ctx->n_buffers].size = size;
|
||||
|
||||
if (ctx->device.maxBufferLength < aligned_size) {
|
||||
fprintf(stderr, "%s: buffer '%s' size %zu is larger than buffer maximum of %zu\n", __func__, name, aligned_size, ctx->device.maxBufferLength);
|
||||
return false;
|
||||
}
|
||||
ctx->buffers[ctx->n_buffers].metal = [ctx->device newBufferWithBytesNoCopy:data length:aligned_size options:MTLResourceStorageModeShared deallocator:nil];
|
||||
|
||||
if (ctx->buffers[ctx->n_buffers].metal == nil) {
|
||||
fprintf(stderr, "%s: failed to allocate '%-16s' buffer, size = %8.2f MB\n", __func__, name, aligned_size / 1024.0 / 1024.0);
|
||||
return false;
|
||||
} else {
|
||||
fprintf(stderr, "%s: allocated '%-16s' buffer, size = %8.2f MB\n", __func__, name, aligned_size / 1024.0 / 1024.0);
|
||||
}
|
||||
|
||||
++ctx->n_buffers;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
void ggml_metal_set_tensor(
|
||||
struct ggml_metal_context * ctx,
|
||||
struct ggml_tensor * t) {
|
||||
metal_printf("%s: set input for tensor '%s'\n", __func__, t->name);
|
||||
|
||||
size_t offs;
|
||||
id<MTLBuffer> id_dst = ggml_metal_get_buffer(ctx, t, &offs);
|
||||
|
||||
memcpy((void *) ((uint8_t *) id_dst.contents + offs), t->data, ggml_nbytes(t));
|
||||
}
|
||||
|
||||
void ggml_metal_get_tensor(
|
||||
struct ggml_metal_context * ctx,
|
||||
struct ggml_tensor * t) {
|
||||
metal_printf("%s: extract results for tensor '%s'\n", __func__, t->name);
|
||||
|
||||
size_t offs;
|
||||
id<MTLBuffer> id_src = ggml_metal_get_buffer(ctx, t, &offs);
|
||||
|
||||
memcpy(t->data, (void *) ((uint8_t *) id_src.contents + offs), ggml_nbytes(t));
|
||||
}
|
||||
|
||||
void ggml_metal_graph_compute(
|
||||
struct ggml_metal_context * ctx,
|
||||
struct ggml_cgraph * gf) {
|
||||
metal_printf("%s: evaluating graph\n", __func__);
|
||||
|
||||
size_t offs_src0 = 0;
|
||||
size_t offs_src1 = 0;
|
||||
size_t offs_dst = 0;
|
||||
|
||||
id<MTLCommandBuffer> command_buffer = [ctx->queue commandBuffer];
|
||||
id<MTLComputeCommandEncoder> encoder = nil;
|
||||
|
||||
for (int i = 0; i < gf->n_nodes; ++i) {
|
||||
//metal_printf("%s: encoding node %3d, op = %8s\n", __func__, i, ggml_op_name(gf->nodes[i]->op));
|
||||
|
||||
struct ggml_tensor * src0 = gf->nodes[i]->src0;
|
||||
struct ggml_tensor * src1 = gf->nodes[i]->src1;
|
||||
struct ggml_tensor * dst = gf->nodes[i];
|
||||
|
||||
const int64_t ne00 = src0 ? src0->ne[0] : 0;
|
||||
const int64_t ne01 = src0 ? src0->ne[1] : 0;
|
||||
const int64_t ne02 = src0 ? src0->ne[2] : 0;
|
||||
const int64_t ne03 = src0 ? src0->ne[3] : 0;
|
||||
|
||||
const uint64_t nb00 = src0 ? src0->nb[0] : 0;
|
||||
const uint64_t nb01 = src0 ? src0->nb[1] : 0;
|
||||
const uint64_t nb02 = src0 ? src0->nb[2] : 0;
|
||||
const uint64_t nb03 = src0 ? src0->nb[3] : 0;
|
||||
|
||||
const int64_t ne10 = src1 ? src1->ne[0] : 0;
|
||||
const int64_t ne11 = src1 ? src1->ne[1] : 0;
|
||||
const int64_t ne12 = src1 ? src1->ne[2] : 0;
|
||||
const int64_t ne13 = src1 ? src1->ne[3] : 0; UNUSED(ne13);
|
||||
|
||||
const uint64_t nb10 = src1 ? src1->nb[0] : 0;
|
||||
const uint64_t nb11 = src1 ? src1->nb[1] : 0;
|
||||
const uint64_t nb12 = src1 ? src1->nb[2] : 0;
|
||||
const uint64_t nb13 = src1 ? src1->nb[3] : 0; UNUSED(nb13);
|
||||
|
||||
const int64_t ne0 = dst ? dst->ne[0] : 0;
|
||||
const int64_t ne1 = dst ? dst->ne[1] : 0;
|
||||
const int64_t ne2 = dst ? dst->ne[2] : 0;
|
||||
const int64_t ne3 = dst ? dst->ne[3] : 0;
|
||||
|
||||
const uint64_t nb0 = dst ? dst->nb[0] : 0;
|
||||
const uint64_t nb1 = dst ? dst->nb[1] : 0;
|
||||
const uint64_t nb2 = dst ? dst->nb[2] : 0;
|
||||
const uint64_t nb3 = dst ? dst->nb[3] : 0;
|
||||
|
||||
const enum ggml_type src0t = src0 ? src0->type : GGML_TYPE_COUNT;
|
||||
const enum ggml_type src1t = src1 ? src1->type : GGML_TYPE_COUNT;
|
||||
const enum ggml_type dstt = dst ? dst->type : GGML_TYPE_COUNT;
|
||||
|
||||
id<MTLBuffer> id_src0 = src0 ? ggml_metal_get_buffer(ctx, src0, &offs_src0) : nil;
|
||||
id<MTLBuffer> id_src1 = src1 ? ggml_metal_get_buffer(ctx, src1, &offs_src1) : nil;
|
||||
id<MTLBuffer> id_dst = dst ? ggml_metal_get_buffer(ctx, dst, &offs_dst) : nil;
|
||||
|
||||
//metal_printf("%s: op - %s\n", __func__, ggml_op_name(dst->op));
|
||||
//if (src0) {
|
||||
// metal_printf("%s: src0 - %4s [%5lld, %5lld, %5lld], %d, %s\n", __func__, ggml_type_name(src0t), ne00, ne01, ne02,
|
||||
// ggml_is_contiguous(src0), src0->name);
|
||||
//}
|
||||
//if (src1) {
|
||||
// metal_printf("%s: src1 - %4s [%5lld, %5lld, %5lld], %d, %s\n", __func__, ggml_type_name(src1t), ne10, ne11, ne12,
|
||||
// ggml_is_contiguous(src1), src1->name);
|
||||
//}
|
||||
//if (dst) {
|
||||
// metal_printf("%s: dst - %4s [%5lld, %5lld, %5lld], 1, %s\n", __func__, ggml_type_name(dstt), ne0, ne1, ne2,
|
||||
// dst->name);
|
||||
//}
|
||||
|
||||
switch (dst->op) {
|
||||
case GGML_OP_RESHAPE:
|
||||
case GGML_OP_VIEW:
|
||||
case GGML_OP_TRANSPOSE:
|
||||
case GGML_OP_PERMUTE:
|
||||
{
|
||||
// noop
|
||||
} break;
|
||||
case GGML_OP_ADD:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_add];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
|
||||
const int64_t n = ggml_nelements(dst);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_MUL:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
if (ggml_nelements(src1) == ne10) {
|
||||
// src1 is a row
|
||||
[encoder setComputePipelineState:ctx->pipeline_mul_row];
|
||||
} else {
|
||||
[encoder setComputePipelineState:ctx->pipeline_mul];
|
||||
}
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:3];
|
||||
|
||||
const int64_t n = ggml_nelements(dst);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_SCALE:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
const float scale = *(const float *) src1->data;
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_scale];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
[encoder setBytes:&scale length:sizeof(scale) atIndex:2];
|
||||
|
||||
const int64_t n = ggml_nelements(dst);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_SILU:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_silu];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
|
||||
const int64_t n = ggml_nelements(dst);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_RELU:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_relu];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
|
||||
const int64_t n = ggml_nelements(dst);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_SOFT_MAX:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
const int nth = 32;
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_soft_max];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:2];
|
||||
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:3];
|
||||
[encoder setBytes:&ne02 length:sizeof(ne02) atIndex:4];
|
||||
[encoder setThreadgroupMemoryLength:nth*sizeof(float) atIndex:0];
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_DIAG_MASK_INF:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
const int n_past = ((int32_t *)(src1->data))[0];
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_diag_mask_inf];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:2];
|
||||
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:3];
|
||||
[encoder setBytes:&n_past length:sizeof(int) atIndex:4];
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne00, ne01, ne02) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_MUL_MAT:
|
||||
{
|
||||
// TODO: needs to be updated after PR: https://github.com/ggerganov/ggml/pull/224
|
||||
|
||||
GGML_ASSERT(ne00 == ne10);
|
||||
GGML_ASSERT(ne02 == ne12);
|
||||
|
||||
if (ggml_is_contiguous(src0) &&
|
||||
ggml_is_contiguous(src1) &&
|
||||
(src0t == GGML_TYPE_F32 || src0t == GGML_TYPE_F16) && ne11 > 1) {
|
||||
|
||||
if (encoder != nil) {
|
||||
[encoder endEncoding];
|
||||
encoder = nil;
|
||||
}
|
||||
|
||||
MPSDataType src0dt = src0t == GGML_TYPE_F32 ? MPSDataTypeFloat32 : MPSDataTypeFloat16;
|
||||
MPSDataType src1dt = src1t == GGML_TYPE_F32 ? MPSDataTypeFloat32 : MPSDataTypeFloat16;
|
||||
|
||||
// for F32 x F32 we use MPS
|
||||
MPSMatrixDescriptor * desc0 = [MPSMatrixDescriptor
|
||||
matrixDescriptorWithRows:ne01 columns:ne00 rowBytes:src0->nb[1] dataType:src0dt];
|
||||
|
||||
MPSMatrixDescriptor * desc1 = [MPSMatrixDescriptor
|
||||
matrixDescriptorWithRows:ne11 columns:ne10 rowBytes:src1->nb[1] dataType:src1dt];
|
||||
|
||||
MPSMatrixDescriptor * desc = [MPSMatrixDescriptor
|
||||
matrixDescriptorWithRows:ne1 columns:ne0 rowBytes:dst->nb[1] dataType:MPSDataTypeFloat32];
|
||||
|
||||
MPSMatrixMultiplication * mul = [[MPSMatrixMultiplication alloc]
|
||||
initWithDevice:ctx->device transposeLeft:false transposeRight:true
|
||||
resultRows:ne11 resultColumns:ne01 interiorColumns:ne00 alpha:1.0 beta:0.0];
|
||||
|
||||
// we need to do ne02 multiplications
|
||||
// TODO: is there a way to do this in parallel - currently very slow ..
|
||||
// TODO: might be possible to offload part of the computation to ANE using Accelerate's CBLAS
|
||||
for (int64_t i02 = 0; i02 < ne02; ++i02) {
|
||||
size_t offs_src0_cur = offs_src0 + i02*nb02;
|
||||
size_t offs_src1_cur = offs_src1 + i02*nb12;
|
||||
size_t offs_dst_cur = offs_dst + i02*nb2;
|
||||
|
||||
MPSMatrix * mat_src0 = [[MPSMatrix alloc] initWithBuffer:id_src0 offset:offs_src0_cur descriptor:desc0];
|
||||
MPSMatrix * mat_src1 = [[MPSMatrix alloc] initWithBuffer:id_src1 offset:offs_src1_cur descriptor:desc1];
|
||||
MPSMatrix * mat_dst = [[MPSMatrix alloc] initWithBuffer:id_dst offset:offs_dst_cur descriptor:desc ];
|
||||
|
||||
[mul encodeToCommandBuffer:command_buffer leftMatrix:mat_src1 rightMatrix:mat_src0 resultMatrix:mat_dst];
|
||||
}
|
||||
} else {
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
int nth0 = 32;
|
||||
int nth1 = 1;
|
||||
|
||||
// use custom matrix x vector kernel
|
||||
switch (src0t) {
|
||||
case GGML_TYPE_Q4_0:
|
||||
{
|
||||
GGML_ASSERT(ne02 == 1);
|
||||
GGML_ASSERT(ne12 == 1);
|
||||
|
||||
nth0 = 8;
|
||||
nth1 = 4;
|
||||
[encoder setComputePipelineState:ctx->pipeline_mul_mat_q4_0_f32];
|
||||
} break;
|
||||
case GGML_TYPE_F16:
|
||||
{
|
||||
GGML_ASSERT(ne02 == ne12);
|
||||
|
||||
nth0 = 32;
|
||||
nth1 = 1;
|
||||
[encoder setComputePipelineState:ctx->pipeline_mul_mat_f16_f32];
|
||||
} break;
|
||||
default: GGML_ASSERT(false && "not implemented");
|
||||
};
|
||||
|
||||
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:3];
|
||||
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:4];
|
||||
[encoder setBytes:&nb00 length:sizeof(nb00) atIndex:5];
|
||||
[encoder setBytes:&nb01 length:sizeof(nb01) atIndex:6];
|
||||
[encoder setBytes:&nb02 length:sizeof(nb02) atIndex:7];
|
||||
[encoder setBytes:&ne10 length:sizeof(ne10) atIndex:8];
|
||||
[encoder setBytes:&ne11 length:sizeof(ne11) atIndex:9];
|
||||
[encoder setBytes:&nb10 length:sizeof(nb10) atIndex:10];
|
||||
[encoder setBytes:&nb11 length:sizeof(nb11) atIndex:11];
|
||||
[encoder setBytes:&nb12 length:sizeof(nb12) atIndex:12];
|
||||
[encoder setBytes:&ne0 length:sizeof(ne0) atIndex:13];
|
||||
[encoder setBytes:&ne1 length:sizeof(ne1) atIndex:14];
|
||||
|
||||
if (src0t == GGML_TYPE_Q4_0) {
|
||||
[encoder setThreadgroupMemoryLength:nth0*nth1*sizeof(float) atIndex:0];
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, 1) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)];
|
||||
} else {
|
||||
[encoder setThreadgroupMemoryLength:nth0*sizeof(float) atIndex:0];
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01, ne11, ne12) threadsPerThreadgroup:MTLSizeMake(nth0, nth1, 1)];
|
||||
}
|
||||
}
|
||||
} break;
|
||||
case GGML_OP_GET_ROWS:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
switch (src0->type) {
|
||||
case GGML_TYPE_Q4_0: [encoder setComputePipelineState:ctx->pipeline_get_rows_q4_0]; break;
|
||||
default: GGML_ASSERT(false && "not implemented");
|
||||
}
|
||||
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_src1 offset:offs_src1 atIndex:1];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
[encoder setBytes:&(src0->ne[0]) length:sizeof( int64_t) atIndex:3];
|
||||
[encoder setBytes:&(src0->nb[1]) length:sizeof(uint64_t) atIndex:4];
|
||||
[encoder setBytes:&(dst->nb[1]) length:sizeof(uint64_t) atIndex:5];
|
||||
|
||||
const int64_t n = ggml_nelements(src1);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(n, 1, 1) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_RMS_NORM:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
const float eps = 1e-6f;
|
||||
|
||||
const int nth = 256;
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_rms_norm];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
|
||||
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:3];
|
||||
[encoder setBytes:&eps length:sizeof( float) atIndex:4];
|
||||
[encoder setThreadgroupMemoryLength:nth*sizeof(float) atIndex:0];
|
||||
|
||||
const int64_t nrows = ggml_nrows(src0);
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(nrows, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_ROPE:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
const int n_dims = ((int32_t *) src1->data)[1];
|
||||
const int mode = ((int32_t *) src1->data)[2];
|
||||
|
||||
const int n_past = ((int32_t *)(src1->data))[0];
|
||||
|
||||
[encoder setComputePipelineState:ctx->pipeline_rope];
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
|
||||
[encoder setBytes:&ne01 length:sizeof( int64_t) atIndex:3];
|
||||
[encoder setBytes:&ne02 length:sizeof( int64_t) atIndex:4];
|
||||
[encoder setBytes:&ne03 length:sizeof( int64_t) atIndex:5];
|
||||
[encoder setBytes:&nb00 length:sizeof(uint64_t) atIndex:6];
|
||||
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:7];
|
||||
[encoder setBytes:&nb02 length:sizeof(uint64_t) atIndex:8];
|
||||
[encoder setBytes:&nb03 length:sizeof(uint64_t) atIndex:9];
|
||||
[encoder setBytes:&ne0 length:sizeof( int64_t) atIndex:10];
|
||||
[encoder setBytes:&ne1 length:sizeof( int64_t) atIndex:11];
|
||||
[encoder setBytes:&ne2 length:sizeof( int64_t) atIndex:12];
|
||||
[encoder setBytes:&ne3 length:sizeof( int64_t) atIndex:13];
|
||||
[encoder setBytes:&nb0 length:sizeof(uint64_t) atIndex:14];
|
||||
[encoder setBytes:&nb1 length:sizeof(uint64_t) atIndex:15];
|
||||
[encoder setBytes:&nb2 length:sizeof(uint64_t) atIndex:16];
|
||||
[encoder setBytes:&nb3 length:sizeof(uint64_t) atIndex:17];
|
||||
[encoder setBytes:&n_past length:sizeof( int) atIndex:18];
|
||||
[encoder setBytes:&n_dims length:sizeof( int) atIndex:19];
|
||||
[encoder setBytes:&mode length:sizeof( int) atIndex:20];
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(1, 1, 1)];
|
||||
} break;
|
||||
case GGML_OP_CPY:
|
||||
{
|
||||
if (encoder == nil) {
|
||||
encoder = [command_buffer computeCommandEncoder];
|
||||
}
|
||||
|
||||
const int nth = 32;
|
||||
|
||||
switch (src0t) {
|
||||
case GGML_TYPE_F32:
|
||||
{
|
||||
switch (dstt) {
|
||||
case GGML_TYPE_F16: [encoder setComputePipelineState:ctx->pipeline_cpy_f32_f16]; break;
|
||||
case GGML_TYPE_F32: [encoder setComputePipelineState:ctx->pipeline_cpy_f32_f32]; break;
|
||||
default: GGML_ASSERT(false && "not implemented");
|
||||
};
|
||||
} break;
|
||||
default: GGML_ASSERT(false && "not implemented");
|
||||
}
|
||||
|
||||
[encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
|
||||
[encoder setBuffer:id_dst offset:offs_dst atIndex:1];
|
||||
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
|
||||
[encoder setBytes:&ne01 length:sizeof( int64_t) atIndex:3];
|
||||
[encoder setBytes:&ne02 length:sizeof( int64_t) atIndex:4];
|
||||
[encoder setBytes:&ne03 length:sizeof( int64_t) atIndex:5];
|
||||
[encoder setBytes:&nb00 length:sizeof(uint64_t) atIndex:6];
|
||||
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:7];
|
||||
[encoder setBytes:&nb02 length:sizeof(uint64_t) atIndex:8];
|
||||
[encoder setBytes:&nb03 length:sizeof(uint64_t) atIndex:9];
|
||||
[encoder setBytes:&ne0 length:sizeof( int64_t) atIndex:10];
|
||||
[encoder setBytes:&ne1 length:sizeof( int64_t) atIndex:11];
|
||||
[encoder setBytes:&ne2 length:sizeof( int64_t) atIndex:12];
|
||||
[encoder setBytes:&ne3 length:sizeof( int64_t) atIndex:13];
|
||||
[encoder setBytes:&nb0 length:sizeof(uint64_t) atIndex:14];
|
||||
[encoder setBytes:&nb1 length:sizeof(uint64_t) atIndex:15];
|
||||
[encoder setBytes:&nb2 length:sizeof(uint64_t) atIndex:16];
|
||||
[encoder setBytes:&nb3 length:sizeof(uint64_t) atIndex:17];
|
||||
|
||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01, ne02, ne03) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
|
||||
} break;
|
||||
default:
|
||||
fprintf(stderr, "%s: node %3d, op = %8s not implemented\n", __func__, i, ggml_op_name(dst->op));
|
||||
GGML_ASSERT(false);
|
||||
}
|
||||
}
|
||||
|
||||
if (encoder != nil) {
|
||||
[encoder endEncoding];
|
||||
encoder = nil;
|
||||
}
|
||||
|
||||
[command_buffer commit];
|
||||
[command_buffer waitUntilCompleted];
|
||||
|
||||
{
|
||||
const double time_elapsed = [command_buffer GPUEndTime] - [command_buffer GPUStartTime];
|
||||
UNUSED(time_elapsed);
|
||||
|
||||
metal_printf("%s: time elapsed = %f ms\n", __func__, time_elapsed * 1000.0);
|
||||
}
|
||||
}
|
||||
489
ggml-metal.metal
Normal file
489
ggml-metal.metal
Normal file
|
|
@ -0,0 +1,489 @@
|
|||
#include <metal_stdlib>
|
||||
|
||||
using namespace metal;
|
||||
|
||||
#define MAX(x, y) ((x) > (y) ? (x) : (y))
|
||||
|
||||
#define QK4_0 32
|
||||
#define QR4_0 2
|
||||
typedef struct {
|
||||
half d; // delta
|
||||
uint8_t qs[QK4_0 / 2]; // nibbles / quants
|
||||
} block_q4_0;
|
||||
|
||||
static void dequantize_row_q4_0(device const block_q4_0 * x, device float * y, int k) {
|
||||
const int qk = QK4_0;
|
||||
|
||||
assert(k % qk == 0);
|
||||
|
||||
const int nb = k / qk;
|
||||
|
||||
for (int i = 0; i < nb; i++) {
|
||||
const half d = x[i].d;
|
||||
|
||||
for (int j = 0; j < qk/2; ++j) {
|
||||
const int x0 = (x[i].qs[j] & 0x0F) - 8;
|
||||
const int x1 = (x[i].qs[j] >> 4) - 8;
|
||||
|
||||
y[i*qk + j + 0 ] = x0*d;
|
||||
y[i*qk + j + qk/2] = x1*d;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_add(
|
||||
device const float * src0,
|
||||
device const float * src1,
|
||||
device float * dst,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
dst[tpig] = src0[tpig] + src1[tpig];
|
||||
}
|
||||
|
||||
kernel void kernel_mul(
|
||||
device const float * src0,
|
||||
device const float * src1,
|
||||
device float * dst,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
dst[tpig] = src0[tpig] * src1[tpig];
|
||||
}
|
||||
|
||||
// assumption: src1 is a row
|
||||
// broadcast src1 into src0
|
||||
kernel void kernel_mul_row(
|
||||
device const float * src0,
|
||||
device const float * src1,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
dst[tpig] = src0[tpig] * src1[tpig % ne00];
|
||||
}
|
||||
|
||||
kernel void kernel_scale(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
constant float & scale,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
dst[tpig] = src0[tpig] * scale;
|
||||
}
|
||||
|
||||
kernel void kernel_silu(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
float x = src0[tpig];
|
||||
dst[tpig] = x / (1.0f + exp(-x));
|
||||
}
|
||||
|
||||
kernel void kernel_relu(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
dst[tpig] = max(0.0f, src0[tpig]);
|
||||
}
|
||||
|
||||
kernel void kernel_soft_max(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant int64_t & ne02,
|
||||
threadgroup float * buf [[threadgroup(0)]],
|
||||
uint3 tgpig[[threadgroup_position_in_grid]],
|
||||
uint3 tpitg[[thread_position_in_threadgroup]],
|
||||
uint3 ntg[[threads_per_threadgroup]]) {
|
||||
const int64_t i03 = tgpig[2];
|
||||
const int64_t i02 = tgpig[1];
|
||||
const int64_t i01 = tgpig[0];
|
||||
|
||||
device const float * psrc0 = src0 + i03*ne02*ne01*ne00 + i02*ne01*ne00 + i01*ne00;
|
||||
device float * pdst = dst + i03*ne02*ne01*ne00 + i02*ne01*ne00 + i01*ne00;
|
||||
|
||||
// parallel max
|
||||
buf[tpitg[0]] = -INFINITY;
|
||||
for (int i00 = tpitg[0]; i00 < ne00; i00 += ntg[0]) {
|
||||
buf[tpitg[0]] = MAX(buf[tpitg[0]], psrc0[i00]);
|
||||
}
|
||||
|
||||
// reduce
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
for (uint i = ntg[0]/2; i > 0; i /= 2) {
|
||||
if (tpitg[0] < i) {
|
||||
buf[tpitg[0]] = MAX(buf[tpitg[0]], buf[tpitg[0] + i]);
|
||||
}
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
}
|
||||
|
||||
// broadcast
|
||||
if (tpitg[0] == 0) {
|
||||
buf[0] = buf[0];
|
||||
}
|
||||
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
|
||||
const float max = buf[0];
|
||||
|
||||
// parallel sum
|
||||
buf[tpitg[0]] = 0.0f;
|
||||
for (int i00 = tpitg[0]; i00 < ne00; i00 += ntg[0]) {
|
||||
buf[tpitg[0]] += exp(psrc0[i00] - max);
|
||||
}
|
||||
|
||||
// reduce
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
for (uint i = ntg[0]/2; i > 0; i /= 2) {
|
||||
if (tpitg[0] < i) {
|
||||
buf[tpitg[0]] += buf[tpitg[0] + i];
|
||||
}
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
}
|
||||
|
||||
// broadcast
|
||||
if (tpitg[0] == 0) {
|
||||
buf[0] = buf[0];
|
||||
}
|
||||
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
|
||||
const float sum = buf[0];
|
||||
|
||||
for (int i00 = tpitg[0]; i00 < ne00; i00 += ntg[0]) {
|
||||
pdst[i00] = exp(psrc0[i00] - max) / sum;
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_diag_mask_inf(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant int & n_past,
|
||||
uint3 tpig[[thread_position_in_grid]]) {
|
||||
const int64_t i02 = tpig[2];
|
||||
const int64_t i01 = tpig[1];
|
||||
const int64_t i00 = tpig[0];
|
||||
|
||||
if (i00 > n_past + i01) {
|
||||
dst[i02*ne01*ne00 + i01*ne00 + i00] = -INFINITY;
|
||||
} else {
|
||||
dst[i02*ne01*ne00 + i01*ne00 + i00] = src0[i02*ne01*ne00 + i01*ne00 + i00];
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_get_rows_q4_0(
|
||||
device const void * src0,
|
||||
device const int * src1,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb1,
|
||||
uint tpig[[thread_position_in_grid]]) {
|
||||
const int i = tpig;
|
||||
const int r = ((device int32_t *) src1)[i];
|
||||
|
||||
dequantize_row_q4_0(
|
||||
(device const block_q4_0 *) ((device char *) src0 + r*nb01),
|
||||
(device float *) ((device char *) dst + i*nb1), ne00);
|
||||
}
|
||||
|
||||
kernel void kernel_rms_norm(
|
||||
device const void * src0,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant uint64_t & nb01,
|
||||
constant float & eps,
|
||||
threadgroup float * sum [[threadgroup(0)]],
|
||||
uint tgpig[[threadgroup_position_in_grid]],
|
||||
uint tpitg[[thread_position_in_threadgroup]],
|
||||
uint ntg[[threads_per_threadgroup]]) {
|
||||
device const float * x = (device const float *) ((device const char *) src0 + tgpig*nb01);
|
||||
|
||||
// parallel sum
|
||||
sum[tpitg] = 0.0f;
|
||||
for (int i00 = tpitg; i00 < ne00; i00 += ntg) {
|
||||
sum[tpitg] += x[i00] * x[i00];
|
||||
}
|
||||
|
||||
// reduce
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
for (uint i = ntg/2; i > 0; i /= 2) {
|
||||
if (tpitg < i) {
|
||||
sum[tpitg] += sum[tpitg + i];
|
||||
}
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
}
|
||||
|
||||
// broadcast
|
||||
if (tpitg == 0) {
|
||||
sum[0] /= ne00;
|
||||
}
|
||||
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
|
||||
const float mean = sum[0];
|
||||
const float scale = 1.0f/sqrt(mean + eps);
|
||||
|
||||
device float * y = dst + tgpig*ne00;
|
||||
for (int i00 = tpitg; i00 < ne00; i00 += ntg) {
|
||||
y[i00] = x[i00] * scale;
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_mul_mat_q4_0_f32(
|
||||
device const void * src0,
|
||||
device const float * src1,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant uint64_t & nb00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb02,
|
||||
constant int64_t & ne10,
|
||||
constant int64_t & ne11,
|
||||
constant uint64_t & nb10,
|
||||
constant uint64_t & nb11,
|
||||
constant uint64_t & nb12,
|
||||
constant int64_t & ne0,
|
||||
constant int64_t & ne1,
|
||||
threadgroup float * sum [[threadgroup(0)]],
|
||||
uint2 tgpig[[threadgroup_position_in_grid]],
|
||||
uint2 tpig[[thread_position_in_grid]],
|
||||
uint2 tpitg[[thread_position_in_threadgroup]],
|
||||
uint2 tptg[[threads_per_threadgroup]]) {
|
||||
const int nb = ne00/QK4_0;
|
||||
|
||||
const int64_t r0 = tgpig.x;
|
||||
const int64_t r1 = tgpig.y;
|
||||
|
||||
device const block_q4_0 * x = (device const block_q4_0 *) src0 + r0*nb;
|
||||
device const float * y = (device const float *) src1 + r1*ne10;
|
||||
|
||||
const uint nth = tptg.x*tptg.y;
|
||||
const uint ith = tptg.y*tpitg.x + tpitg.y;
|
||||
|
||||
sum[ith] = 0.0f;
|
||||
|
||||
for (int i = tpitg.x; i < nb; i += tptg.x) {
|
||||
device const uchar4 * x0p = (device const uchar4 *) (x + i)->qs;
|
||||
device const float4 * y0p = (device const float4 *) (y + i*QK4_0);
|
||||
|
||||
const float d = (float)((x + i)->d);
|
||||
|
||||
const uchar4 x0v = *(x0p + tpitg.y);
|
||||
const float4 y0v = *(y0p + tpitg.y + 0);
|
||||
const float4 y1v = *(y0p + tpitg.y + 4);
|
||||
|
||||
float acc = 0.0f;
|
||||
|
||||
for (int j = 0; j < 4; ++j) {
|
||||
const int x0 = x0v[j] & 0x0F;
|
||||
const int x1 = x0v[j] >> 4;
|
||||
|
||||
const float y0 = y0v[j];
|
||||
const float y1 = y1v[j];
|
||||
|
||||
acc += (x0 - 8)*y0 + (x1 - 8)*y1;
|
||||
}
|
||||
|
||||
sum[ith] += acc*d;
|
||||
}
|
||||
|
||||
// accumulate the sum from all threads in the threadgroup
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
for (uint i = nth/2; i > 0; i /= 2) {
|
||||
if (ith < i) {
|
||||
sum[ith] += sum[ith + i];
|
||||
}
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
}
|
||||
|
||||
if (ith == 0) {
|
||||
dst[r1*ne0 + r0] = sum[0];
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_mul_mat_f16_f32(
|
||||
device const char * src0,
|
||||
device const char * src1,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant uint64_t & nb00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb02,
|
||||
constant int64_t & ne10,
|
||||
constant int64_t & ne11,
|
||||
constant uint64_t & nb10,
|
||||
constant uint64_t & nb11,
|
||||
constant uint64_t & nb12,
|
||||
constant int64_t & ne0,
|
||||
constant int64_t & ne1,
|
||||
threadgroup float * sum [[threadgroup(0)]],
|
||||
uint3 tgpig[[threadgroup_position_in_grid]],
|
||||
uint3 tpig[[thread_position_in_grid]],
|
||||
uint3 tpitg[[thread_position_in_threadgroup]],
|
||||
uint3 tptg[[threads_per_threadgroup]]) {
|
||||
const int64_t r0 = tgpig.x;
|
||||
const int64_t r1 = tgpig.y;
|
||||
const int64_t im = tgpig.z;
|
||||
|
||||
device const half * x = (device const half *) (src0 + r0*nb01 + im*nb02);
|
||||
device const float * y = (device const float *) (src1 + r1*nb11 + im*nb12);
|
||||
|
||||
sum[tpitg.x] = 0.0f;
|
||||
|
||||
for (int i = tpitg.x; i < ne00; i += tptg.x) {
|
||||
sum[tpitg.x] += (float) x[i] * (float) y[i];
|
||||
}
|
||||
|
||||
// accumulate the sum from all threads in the threadgroup
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
for (uint i = tptg.x/2; i > 0; i /= 2) {
|
||||
if (tpitg.x < i) {
|
||||
sum[tpitg.x] += sum[tpitg.x + i];
|
||||
}
|
||||
threadgroup_barrier(mem_flags::mem_threadgroup);
|
||||
}
|
||||
|
||||
if (tpitg.x == 0) {
|
||||
dst[im*ne1*ne0 + r1*ne0 + r0] = sum[0];
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_rope(
|
||||
device const void * src0,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant int64_t & ne02,
|
||||
constant int64_t & ne03,
|
||||
constant uint64_t & nb00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb02,
|
||||
constant uint64_t & nb03,
|
||||
constant int64_t & ne0,
|
||||
constant int64_t & ne1,
|
||||
constant int64_t & ne2,
|
||||
constant int64_t & ne3,
|
||||
constant uint64_t & nb0,
|
||||
constant uint64_t & nb1,
|
||||
constant uint64_t & nb2,
|
||||
constant uint64_t & nb3,
|
||||
constant int & n_past,
|
||||
constant int & n_dims,
|
||||
constant int & mode,
|
||||
uint3 tpig[[thread_position_in_grid]]) {
|
||||
const int64_t i3 = tpig[2];
|
||||
const int64_t i2 = tpig[1];
|
||||
const int64_t i1 = tpig[0];
|
||||
|
||||
const bool is_neox = mode & 2;
|
||||
const float theta_scale = pow(10000.0, -2.0f/n_dims);
|
||||
|
||||
const int64_t p = ((mode & 1) == 0 ? n_past + i2 : i2);
|
||||
|
||||
float theta = (float)p;
|
||||
|
||||
if (!is_neox) {
|
||||
for (int64_t i0 = 0; i0 < ne0; i0 += 2) {
|
||||
const float cos_theta = cos(theta);
|
||||
const float sin_theta = sin(theta);
|
||||
|
||||
theta *= theta_scale;
|
||||
|
||||
device const float * const src = (device float *)((device char *) src0 + i3*nb03 + i2*nb02 + i1*nb01 + i0*nb00);
|
||||
device float * dst_data = (device float *)((device char *) dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0);
|
||||
|
||||
const float x0 = src[0];
|
||||
const float x1 = src[1];
|
||||
|
||||
dst_data[0] = x0*cos_theta - x1*sin_theta;
|
||||
dst_data[1] = x0*sin_theta + x1*cos_theta;
|
||||
}
|
||||
} else {
|
||||
// TODO: implement
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_cpy_f32_f16(
|
||||
device const float * src0,
|
||||
device half * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant int64_t & ne02,
|
||||
constant int64_t & ne03,
|
||||
constant uint64_t & nb00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb02,
|
||||
constant uint64_t & nb03,
|
||||
constant int64_t & ne0,
|
||||
constant int64_t & ne1,
|
||||
constant int64_t & ne2,
|
||||
constant int64_t & ne3,
|
||||
constant uint64_t & nb0,
|
||||
constant uint64_t & nb1,
|
||||
constant uint64_t & nb2,
|
||||
constant uint64_t & nb3,
|
||||
uint3 tgpig[[threadgroup_position_in_grid]],
|
||||
uint3 tpitg[[thread_position_in_threadgroup]],
|
||||
uint3 ntg[[threads_per_threadgroup]]) {
|
||||
const int64_t i03 = tgpig[2];
|
||||
const int64_t i02 = tgpig[1];
|
||||
const int64_t i01 = tgpig[0];
|
||||
|
||||
const int64_t n = i03*ne02*ne01*ne00 + i02*ne01*ne00 + i01*ne00;
|
||||
|
||||
const int64_t i3 = n / (ne2*ne1*ne0);
|
||||
const int64_t i2 = (n - i3*ne2*ne1*ne0) / (ne1*ne0);
|
||||
const int64_t i1 = (n - i3*ne2*ne1*ne0 - i2*ne1*ne0) / ne0;
|
||||
const int64_t i0 = (n - i3*ne2*ne1*ne0 - i2*ne1*ne0 - i1*ne0);
|
||||
|
||||
device half * dst_data = (device half *) ((device char *) dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0);
|
||||
|
||||
for (int64_t i00 = tpitg.x; i00 < ne00; i00 += ntg.x) {
|
||||
device const float * src = (device float *)((device char *) src0 + i03*nb03 + i02*nb02 + i01*nb01 + i00*nb00);
|
||||
|
||||
dst_data[i00] = src[0];
|
||||
}
|
||||
}
|
||||
|
||||
kernel void kernel_cpy_f32_f32(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant int64_t & ne02,
|
||||
constant int64_t & ne03,
|
||||
constant uint64_t & nb00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb02,
|
||||
constant uint64_t & nb03,
|
||||
constant int64_t & ne0,
|
||||
constant int64_t & ne1,
|
||||
constant int64_t & ne2,
|
||||
constant int64_t & ne3,
|
||||
constant uint64_t & nb0,
|
||||
constant uint64_t & nb1,
|
||||
constant uint64_t & nb2,
|
||||
constant uint64_t & nb3,
|
||||
uint3 tgpig[[threadgroup_position_in_grid]],
|
||||
uint3 tpitg[[thread_position_in_threadgroup]],
|
||||
uint3 ntg[[threads_per_threadgroup]]) {
|
||||
const int64_t i03 = tgpig[2];
|
||||
const int64_t i02 = tgpig[1];
|
||||
const int64_t i01 = tgpig[0];
|
||||
|
||||
const int64_t n = i03*ne02*ne01*ne00 + i02*ne01*ne00 + i01*ne00;
|
||||
|
||||
const int64_t i3 = n / (ne2*ne1*ne0);
|
||||
const int64_t i2 = (n - i3*ne2*ne1*ne0) / (ne1*ne0);
|
||||
const int64_t i1 = (n - i3*ne2*ne1*ne0 - i2*ne1*ne0) / ne0;
|
||||
const int64_t i0 = (n - i3*ne2*ne1*ne0 - i2*ne1*ne0 - i1*ne0);
|
||||
|
||||
device float * dst_data = (device float *) ((device char *) dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0);
|
||||
|
||||
for (int64_t i00 = tpitg.x; i00 < ne00; i00 += ntg.x) {
|
||||
device const float * src = (device float *)((device char *) src0 + i03*nb03 + i02*nb02 + i01*nb01 + i00*nb00);
|
||||
|
||||
dst_data[i00] = src[0];
|
||||
}
|
||||
}
|
||||
206
ggml-opencl.cpp
206
ggml-opencl.cpp
|
|
@ -3,6 +3,7 @@
|
|||
#include <array>
|
||||
#include <atomic>
|
||||
#include <sstream>
|
||||
#include <vector>
|
||||
|
||||
#define CL_TARGET_OPENCL_VERSION 110
|
||||
#include <clblast.h>
|
||||
|
|
@ -197,6 +198,18 @@ __kernel void KERNEL_NAME(__global X_TYPE* x, __local float* tmp, __global float
|
|||
}
|
||||
);
|
||||
|
||||
std::string mul_template = MULTILINE_QUOTE(
|
||||
__kernel void KERNEL_NAME(__global TYPE* x, const int x_offset, __global TYPE* y, const int y_offset, __global TYPE* dst, const int dst_offset, const int ky) {
|
||||
const int i = get_group_id(0)*get_local_size(0) + get_local_id(0);
|
||||
|
||||
if (i >= get_global_size(0)) {
|
||||
return;
|
||||
}
|
||||
|
||||
dst[dst_offset + i] = x[x_offset + i] * y[y_offset + i%ky];
|
||||
}
|
||||
);
|
||||
|
||||
#define CL_CHECK(err) \
|
||||
do { \
|
||||
cl_int err_ = (err); \
|
||||
|
|
@ -239,6 +252,13 @@ std::array<std::string, 30> dequant_mul_mat_vec_str_values = {
|
|||
"convert_mul_mat_vec_f16", "half", "1", "1", "convert_f16"
|
||||
};
|
||||
|
||||
std::array<std::string, 2> mul_str_keys = {
|
||||
"KERNEL_NAME", "TYPE"
|
||||
};
|
||||
std::array<std::string, 2> mul_str_values = {
|
||||
"mul_f32", "float"
|
||||
};
|
||||
|
||||
std::string& replace(std::string& s, const std::string& from, const std::string& to) {
|
||||
size_t pos = 0;
|
||||
while ((pos = s.find(from, pos)) != std::string::npos) {
|
||||
|
|
@ -261,6 +281,13 @@ std::string generate_kernels() {
|
|||
src << dequant_kernel << '\n';
|
||||
src << dmmv_kernel << '\n';
|
||||
}
|
||||
for (size_t i = 0; i < mul_str_values.size(); i += mul_str_keys.size()) {
|
||||
std::string mul_kernel = mul_template;
|
||||
for (size_t j = 0; j < mul_str_keys.size(); j++) {
|
||||
replace(mul_kernel, mul_str_keys[j], mul_str_values[i + j]);
|
||||
}
|
||||
src << mul_kernel << '\n';
|
||||
}
|
||||
return src.str();
|
||||
}
|
||||
|
||||
|
|
@ -272,6 +299,7 @@ static cl_program program;
|
|||
static cl_kernel convert_row_f16_cl;
|
||||
static cl_kernel dequantize_row_q4_0_cl, dequantize_row_q4_1_cl, dequantize_row_q5_0_cl, dequantize_row_q5_1_cl, dequantize_row_q8_0_cl;
|
||||
static cl_kernel dequantize_mul_mat_vec_q4_0_cl, dequantize_mul_mat_vec_q4_1_cl, dequantize_mul_mat_vec_q5_0_cl, dequantize_mul_mat_vec_q5_1_cl, dequantize_mul_mat_vec_q8_0_cl, convert_mul_mat_vec_f16_cl;
|
||||
static cl_kernel mul_f32_cl;
|
||||
static bool fp16_support;
|
||||
|
||||
static cl_program build_program_from_source(cl_context ctx, cl_device_id dev, const char* program_buffer) {
|
||||
|
|
@ -469,16 +497,11 @@ void ggml_cl_init(void) {
|
|||
|
||||
size_t ext_str_size;
|
||||
clGetDeviceInfo(device, CL_DEVICE_EXTENSIONS, 0, NULL, &ext_str_size);
|
||||
char* ext_buffer = (char*) malloc(sizeof(char) * ext_str_size);
|
||||
char *ext_buffer = (char *)alloca(ext_str_size + 1);
|
||||
clGetDeviceInfo(device, CL_DEVICE_EXTENSIONS, ext_str_size, ext_buffer, NULL);
|
||||
ext_buffer[ext_str_size] = '\0'; // ensure it is null terminated
|
||||
// Check if ext_buffer contains cl_khr_fp16
|
||||
for (size_t i = 0; i < ext_str_size - 12; i++) {
|
||||
if (memcmp(ext_buffer + i, "cl_khr_fp16", 11) == 0) {
|
||||
fp16_support = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
free(ext_buffer);
|
||||
fp16_support = strstr(ext_buffer, "cl_khr_fp16") != NULL;
|
||||
fprintf(stderr, "ggml_opencl: device FP16 support: %s\n", fp16_support ? "true" : "false");
|
||||
|
||||
cl_context_properties properties[] = {
|
||||
|
|
@ -513,6 +536,9 @@ void ggml_cl_init(void) {
|
|||
CL_CHECK((dequantize_mul_mat_vec_q5_1_cl = clCreateKernel(program, "dequantize_mul_mat_vec_q5_1", &err), err));
|
||||
CL_CHECK((dequantize_mul_mat_vec_q8_0_cl = clCreateKernel(program, "dequantize_mul_mat_vec_q8_0", &err), err));
|
||||
CL_CHECK((convert_mul_mat_vec_f16_cl = clCreateKernel(program, "convert_mul_mat_vec_f16", &err), err));
|
||||
|
||||
// mul kernel
|
||||
CL_CHECK((mul_f32_cl = clCreateKernel(program, "mul_f32", &err), err));
|
||||
}
|
||||
|
||||
static cl_kernel* ggml_get_to_fp32_cl(ggml_type type) {
|
||||
|
|
@ -649,6 +675,98 @@ static cl_int ggml_cl_h2d_tensor_2d(cl_command_queue queue, cl_mem dst, size_t o
|
|||
return err;
|
||||
}
|
||||
|
||||
static void ggml_cl_mul_f32(const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
|
||||
GGML_ASSERT(src1->backend == GGML_BACKEND_CL);
|
||||
const int64_t ne00 = src0->ne[0];
|
||||
const int64_t ne01 = src0->ne[1];
|
||||
const int64_t ne02 = src0->ne[2];
|
||||
const int64_t ne03 = src0->ne[2];
|
||||
const int64_t ne0 = ne00 * ne01 * ne02 * ne03;
|
||||
const int64_t ne10 = src1->ne[0];
|
||||
const int64_t ne11 = src1->ne[1];
|
||||
const int64_t ne12 = src1->ne[2];
|
||||
const int64_t ne13 = src1->ne[3];
|
||||
const int64_t nb10 = src1->nb[0];
|
||||
const int nb2 = dst->nb[2];
|
||||
const int nb3 = dst->nb[3];
|
||||
size_t x_size;
|
||||
size_t d_size;
|
||||
|
||||
cl_mem d_X = ggml_cl_pool_malloc(ne0 * sizeof(float), &x_size, CL_MEM_READ_ONLY); // src0
|
||||
cl_mem d_Y = (cl_mem) src1->data; // src1 is already on device, broadcasted.
|
||||
cl_mem d_D = ggml_cl_pool_malloc(ne0 * sizeof(float), &d_size, CL_MEM_WRITE_ONLY); // dst
|
||||
|
||||
for (int64_t i03 = 0; i03 < ne03; i03++) {
|
||||
for (int64_t i02 = 0; i02 < ne02; i02++) {
|
||||
const int i0 = i03*ne02 + i02;
|
||||
|
||||
cl_event ev;
|
||||
|
||||
// copy src0 to device
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, d_X, i0, src0, i03, i02, &ev));
|
||||
|
||||
if (nb10 == sizeof(float)) {
|
||||
// Contiguous, avoid overhead from queueing many kernel runs
|
||||
const int64_t i13 = i03%ne13;
|
||||
const int64_t i12 = i02%ne12;
|
||||
const int i1 = i13*ne12*ne11 + i12*ne11;
|
||||
|
||||
cl_int x_offset = 0;
|
||||
cl_int y_offset = i1*ne10;
|
||||
cl_int d_offset = 0;
|
||||
|
||||
size_t global = ne00 * ne01;
|
||||
cl_int ky = ne10;
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 0, sizeof(cl_mem), &d_X));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 1, sizeof(cl_int), &x_offset));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 2, sizeof(cl_mem), &d_Y));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 3, sizeof(cl_int), &y_offset));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 4, sizeof(cl_mem), &d_D));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 5, sizeof(cl_int), &d_offset));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 6, sizeof(cl_int), &ky));
|
||||
CL_CHECK(clEnqueueNDRangeKernel(queue, mul_f32_cl, 1, NULL, &global, NULL, 1, &ev, NULL));
|
||||
} else {
|
||||
for (int64_t i01 = 0; i01 < ne01; i01++) {
|
||||
const int64_t i13 = i03%ne13;
|
||||
const int64_t i12 = i02%ne12;
|
||||
const int64_t i11 = i01%ne11;
|
||||
const int i1 = i13*ne12*ne11 + i12*ne11 + i11;
|
||||
|
||||
cl_int x_offset = i01*ne00;
|
||||
cl_int y_offset = i1*ne10;
|
||||
cl_int d_offset = i01*ne00;
|
||||
|
||||
// compute
|
||||
size_t global = ne00;
|
||||
cl_int ky = ne10;
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 0, sizeof(cl_mem), &d_X));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 1, sizeof(cl_int), &x_offset));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 2, sizeof(cl_mem), &d_Y));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 3, sizeof(cl_int), &y_offset));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 4, sizeof(cl_mem), &d_D));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 5, sizeof(cl_int), &d_offset));
|
||||
CL_CHECK(clSetKernelArg(mul_f32_cl, 6, sizeof(cl_int), &ky));
|
||||
CL_CHECK(clEnqueueNDRangeKernel(queue, mul_f32_cl, 1, NULL, &global, NULL, 1, &ev, NULL));
|
||||
}
|
||||
}
|
||||
|
||||
CL_CHECK(clReleaseEvent(ev));
|
||||
CL_CHECK(clFinish(queue));
|
||||
|
||||
// copy dst to host
|
||||
float * d = (float *) ((char *) dst->data + i02*nb2 + i03*nb3);
|
||||
CL_CHECK(clEnqueueReadBuffer(queue, d_D, true, 0, sizeof(float) * ne00*ne01, d, 0, NULL, NULL));
|
||||
}
|
||||
}
|
||||
ggml_cl_pool_free(d_X, x_size);
|
||||
ggml_cl_pool_free(d_D, d_size);
|
||||
}
|
||||
|
||||
void ggml_cl_mul(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst) {
|
||||
GGML_ASSERT(src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32);
|
||||
ggml_cl_mul_f32(src0, src1, dst);
|
||||
}
|
||||
|
||||
static void ggml_cl_mul_mat_f32(const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
|
||||
const int64_t ne00 = src0->ne[0];
|
||||
const int64_t ne01 = src0->ne[1];
|
||||
|
|
@ -672,7 +790,7 @@ static void ggml_cl_mul_mat_f32(const ggml_tensor * src0, const ggml_tensor * sr
|
|||
size_t d_size;
|
||||
cl_mem d_X;
|
||||
if (src0->backend == GGML_BACKEND_CL) {
|
||||
d_X = *(cl_mem*) src0->data;
|
||||
d_X = (cl_mem) src0->data;
|
||||
} else {
|
||||
d_X = ggml_cl_pool_malloc(sizeof(ggml_fp16_t) * x_ne, &x_size, CL_MEM_READ_ONLY);
|
||||
}
|
||||
|
|
@ -748,7 +866,7 @@ static void ggml_cl_mul_mat_f16(const ggml_tensor * src0, const ggml_tensor * sr
|
|||
size_t d_size;
|
||||
cl_mem d_X;
|
||||
if (src0->backend == GGML_BACKEND_CL) {
|
||||
d_X = *(cl_mem*) src0->data;
|
||||
d_X = (cl_mem) src0->data;
|
||||
} else {
|
||||
d_X = ggml_cl_pool_malloc(sizeof(ggml_fp16_t) * x_ne, &x_size, CL_MEM_READ_ONLY);
|
||||
}
|
||||
|
|
@ -865,44 +983,48 @@ static void ggml_cl_mul_mat_q_f32(const ggml_tensor * src0, const ggml_tensor *
|
|||
cl_kernel* dmmv = ggml_get_dequantize_mul_mat_vec_cl(type);
|
||||
GGML_ASSERT(to_fp32_cl != nullptr);
|
||||
|
||||
size_t ev_idx = 0;
|
||||
std::vector<cl_event> events;
|
||||
|
||||
for (int64_t i03 = 0; i03 < ne03; i03++) {
|
||||
for (int64_t i02 = 0; i02 < ne02; i02++) {
|
||||
cl_event ev_sgemm;
|
||||
|
||||
// copy src0 to device if necessary
|
||||
if (src0->backend == GGML_BACKEND_CPU) {
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, d_Q, 0, src0, i03, i02, NULL));
|
||||
events.emplace_back();
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, d_Q, 0, src0, i03, i02, events.data() + ev_idx++));
|
||||
} else if (src0->backend == GGML_BACKEND_CL) {
|
||||
d_Q = *(cl_mem*) src0->data;
|
||||
d_Q = (cl_mem) src0->data;
|
||||
} else {
|
||||
GGML_ASSERT(false);
|
||||
}
|
||||
if (mul_mat_vec) { // specialized dequantize_mul_mat_vec kernel
|
||||
// copy src1 to device
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, d_Y, 0, src1, i03, i02, NULL));
|
||||
events.emplace_back();
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, d_Y, 0, src1, i03, i02, events.data() + ev_idx++));
|
||||
|
||||
// compute
|
||||
const size_t global = ne01 * CL_DMMV_BLOCK_SIZE;
|
||||
const size_t local = CL_DMMV_BLOCK_SIZE;
|
||||
const cl_int ncols = ne00;
|
||||
events.emplace_back();
|
||||
CL_CHECK(clSetKernelArg(*dmmv, 0, sizeof(cl_mem), &d_Q));
|
||||
CL_CHECK(clSetKernelArg(*dmmv, 1, sizeof(float) * local, NULL));
|
||||
CL_CHECK(clSetKernelArg(*dmmv, 2, sizeof(cl_mem), &d_Y));
|
||||
CL_CHECK(clSetKernelArg(*dmmv, 3, sizeof(cl_mem), &d_D));
|
||||
CL_CHECK(clSetKernelArg(*dmmv, 4, sizeof(cl_int), &ncols));
|
||||
CL_CHECK(clFinish(queue));
|
||||
CL_CHECK(clEnqueueNDRangeKernel(queue, *dmmv, 1, NULL, &global, &local, 0, NULL, &ev_sgemm));
|
||||
CL_CHECK(clEnqueueNDRangeKernel(queue, *dmmv, 1, NULL, &global, &local, events.size() - 1, events.data(), events.data() + ev_idx++));
|
||||
} else { // general dequantization kernel + CLBlast matrix matrix multiplication
|
||||
// convert src0 to fp32 on device
|
||||
const size_t global = x_ne;
|
||||
CL_CHECK(clSetKernelArg(*to_fp32_cl, 0, sizeof(cl_mem), &d_Q));
|
||||
CL_CHECK(clSetKernelArg(*to_fp32_cl, 1, sizeof(cl_mem), &d_X));
|
||||
CL_CHECK(clFinish(queue));
|
||||
CL_CHECK(clEnqueueNDRangeKernel(queue, *to_fp32_cl, 1, NULL, &global, NULL, 0, NULL, NULL));
|
||||
CL_CHECK(clEnqueueNDRangeKernel(queue, *to_fp32_cl, 1, NULL, &global, NULL, events.size(), !events.empty() ? events.data() : NULL, NULL));
|
||||
|
||||
// copy src1 to device
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, d_Y, 0, src1, i03, i02, NULL));
|
||||
|
||||
events.emplace_back();
|
||||
|
||||
// wait for conversion
|
||||
CL_CHECK(clFinish(queue));
|
||||
|
||||
|
|
@ -915,7 +1037,7 @@ static void ggml_cl_mul_mat_q_f32(const ggml_tensor * src0, const ggml_tensor *
|
|||
d_Y, 0, ne10,
|
||||
beta,
|
||||
d_D, 0, ne01,
|
||||
&queue, &ev_sgemm);
|
||||
&queue, events.data() + ev_idx++);
|
||||
|
||||
if (status != clblast::StatusCode::kSuccess) {
|
||||
GGML_ASSERT(false);
|
||||
|
|
@ -924,8 +1046,13 @@ static void ggml_cl_mul_mat_q_f32(const ggml_tensor * src0, const ggml_tensor *
|
|||
|
||||
// copy dst to host
|
||||
float * d = (float *) ((char *) dst->data + i02*nb2 + i03*nb3);
|
||||
CL_CHECK(clEnqueueReadBuffer(queue, d_D, true, 0, sizeof(float) * d_ne, d, 1, &ev_sgemm, NULL));
|
||||
clReleaseEvent(ev_sgemm);
|
||||
CL_CHECK(clEnqueueReadBuffer(queue, d_D, true, 0, sizeof(float) * d_ne, d, 1, &events[events.size() - 1], NULL));
|
||||
for (auto *event : events) {
|
||||
clReleaseEvent(event);
|
||||
}
|
||||
|
||||
ev_idx = 0;
|
||||
events.clear();
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -1016,14 +1143,13 @@ void ggml_cl_transform_tensor(ggml_tensor * tensor) {
|
|||
const size_t q_sz = ggml_type_size(type) * ne0 * ne1 * ne2 * ne3 / ggml_blck_size(type);
|
||||
|
||||
size_t q_size;
|
||||
cl_mem* dst = (cl_mem*) malloc(sizeof(cl_mem));
|
||||
*dst = ggml_cl_pool_malloc(q_sz, &q_size, CL_MEM_READ_ONLY);
|
||||
cl_mem dst = ggml_cl_pool_malloc(q_sz, &q_size, CL_MEM_READ_ONLY);
|
||||
|
||||
// copy tensor to device
|
||||
for (int64_t i3 = 0; i3 < ne3; i3++) {
|
||||
for (int64_t i2 = 0; i2 < ne2; i2++) {
|
||||
int i = i3*ne2 + i2;
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, *dst, i*ne0*ne1, tensor, i3, i2, NULL));
|
||||
CL_CHECK(ggml_cl_h2d_tensor_2d(queue, dst, i*ne0*ne1, tensor, i3, i2, NULL));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -1032,3 +1158,33 @@ void ggml_cl_transform_tensor(ggml_tensor * tensor) {
|
|||
tensor->data = dst;
|
||||
tensor->backend = GGML_BACKEND_CL;
|
||||
}
|
||||
|
||||
void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, const size_t offset) {
|
||||
cl_int err;
|
||||
FILE * fp = fopen(fname, "rb");
|
||||
|
||||
const size_t size = ggml_nbytes(tensor);
|
||||
|
||||
cl_mem dst;
|
||||
CL_CHECK((dst = clCreateBuffer(context, CL_MEM_READ_ONLY, size, nullptr, &err), err));
|
||||
void * buf_host = malloc(size);
|
||||
|
||||
#ifdef _WIN32
|
||||
int ret = _fseeki64(fp, (__int64) offset, SEEK_SET);
|
||||
#else
|
||||
int ret = fseek(fp, (long) offset, SEEK_SET);
|
||||
#endif
|
||||
GGML_ASSERT(ret == 0); // same
|
||||
|
||||
size_t ret2 = fread(buf_host, size, 1, fp);
|
||||
if (ret2 != 1) {
|
||||
fprintf(stderr, "unexpectedly reached end of file");
|
||||
exit(1);
|
||||
}
|
||||
|
||||
clEnqueueWriteBuffer(queue, dst, CL_TRUE, 0, size, buf_host, 0, nullptr, nullptr);
|
||||
|
||||
tensor->data = dst;
|
||||
free(buf_host);
|
||||
fclose(fp);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -8,6 +8,7 @@ extern "C" {
|
|||
|
||||
void ggml_cl_init(void);
|
||||
|
||||
void ggml_cl_mul(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
|
||||
bool ggml_cl_can_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
|
||||
size_t ggml_cl_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst);
|
||||
void ggml_cl_mul_mat(const struct ggml_tensor * src0, const struct ggml_tensor * src1, struct ggml_tensor * dst, void * wdata, size_t wsize);
|
||||
|
|
@ -16,6 +17,7 @@ void * ggml_cl_host_malloc(size_t size);
|
|||
void ggml_cl_host_free(void * ptr);
|
||||
|
||||
void ggml_cl_transform_tensor(struct ggml_tensor * tensor);
|
||||
void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, size_t offset);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
|
|
|
|||
2246
ggml-quants-k.c
Normal file
2246
ggml-quants-k.c
Normal file
File diff suppressed because it is too large
Load diff
122
ggml-quants-k.h
Normal file
122
ggml-quants-k.h
Normal file
|
|
@ -0,0 +1,122 @@
|
|||
#pragma once
|
||||
|
||||
#include "ggml.h"
|
||||
|
||||
#include <stdint.h>
|
||||
#include <assert.h>
|
||||
#include <stddef.h>
|
||||
|
||||
// Super-block size
|
||||
#define QK_K 256
|
||||
|
||||
//
|
||||
// Super-block quantization structures
|
||||
//
|
||||
|
||||
// 2-bit quantization
|
||||
// weight is represented as x = a * q + b
|
||||
// 16 blocks of 16 elemenets each
|
||||
// Effectively 2.5625 bits per weight
|
||||
typedef struct {
|
||||
uint8_t scales[QK_K/16]; // scales and mins, quantized with 4 bits
|
||||
uint8_t qs[QK_K/4]; // quants
|
||||
ggml_fp16_t d; // super-block scale for quantized scales
|
||||
ggml_fp16_t dmin; // super-block scale for quantized mins
|
||||
} block_q2_k;
|
||||
static_assert(sizeof(block_q2_k) == 2*sizeof(ggml_fp16_t) + QK_K/16 + QK_K/4, "wrong q2_k block size/padding");
|
||||
|
||||
// 3-bit quantization
|
||||
// weight is represented as x = a * q
|
||||
// 16 blocks of 16 elemenets each
|
||||
// Effectively 3.4375 bits per weight
|
||||
typedef struct {
|
||||
uint8_t hmask[QK_K/8]; // quants - high bit
|
||||
uint8_t qs[QK_K/4]; // quants - low 2 bits
|
||||
uint8_t scales[3*QK_K/64]; // scales, quantized with 6 bits
|
||||
ggml_fp16_t d; // super-block scale
|
||||
} block_q3_k;
|
||||
static_assert(sizeof(block_q3_k) == sizeof(ggml_fp16_t) + QK_K / 4 + 11 * QK_K / 64, "wrong q3_k block size/padding");
|
||||
|
||||
// 4-bit quantization
|
||||
// 16 blocks of 32 elements each
|
||||
// weight is represented as x = a * q + b
|
||||
// Effectively 4.5 bits per weight
|
||||
typedef struct {
|
||||
ggml_fp16_t d; // super-block scale for quantized scales
|
||||
ggml_fp16_t dmin; // super-block scale for quantized mins
|
||||
uint8_t scales[3*QK_K/64]; // scales and mins, quantized with 6 bits
|
||||
uint8_t qs[QK_K/2]; // 4--bit quants
|
||||
} block_q4_k;
|
||||
static_assert(sizeof(block_q4_k) == 2*sizeof(ggml_fp16_t) + 3*QK_K/64 + QK_K/2, "wrong q4_k block size/padding");
|
||||
|
||||
// 5-bit quantization
|
||||
// 16 blocks of 32 elements each
|
||||
// weight is represented as x = a * q + b
|
||||
// Effectively 5.5 bits per weight
|
||||
typedef struct {
|
||||
ggml_fp16_t d; // super-block scale for quantized scales
|
||||
ggml_fp16_t dmin; // super-block scale for quantized mins
|
||||
uint8_t scales[3*QK_K/64]; // scales and mins, quantized with 6 bits
|
||||
uint8_t qh[QK_K/8]; // quants, high bit
|
||||
uint8_t qs[QK_K/2]; // quants, low 4 bits
|
||||
} block_q5_k;
|
||||
static_assert(sizeof(block_q5_k) == 2*sizeof(ggml_fp16_t) + 3*QK_K/64 + QK_K/2 + QK_K/8, "wrong q5_k block size/padding");
|
||||
|
||||
// 6-bit quantization
|
||||
// weight is represented as x = a * q
|
||||
// 16 blocks of 16 elemenets each
|
||||
// Effectively 6.5625 bits per weight
|
||||
typedef struct {
|
||||
uint8_t ql[QK_K/2]; // quants, lower 4 bits
|
||||
uint8_t qh[QK_K/4]; // quants, upper 2 bits
|
||||
int8_t scales[QK_K/16]; // scales, quantized with 8 bits
|
||||
ggml_fp16_t d; // super-block scale
|
||||
} block_q6_k;
|
||||
static_assert(sizeof(block_q6_k) == sizeof(ggml_fp16_t) + QK_K / 16 + 3*QK_K/4, "wrong q6_k block size/padding");
|
||||
|
||||
// This is only used for intermediate quantization and dot products
|
||||
typedef struct {
|
||||
float d; // delta
|
||||
int8_t qs[QK_K]; // quants
|
||||
int16_t bsums[QK_K/16]; // sum of quants in groups of 16
|
||||
} block_q8_k;
|
||||
static_assert(sizeof(block_q8_k) == sizeof(float) + QK_K + QK_K/16*sizeof(int16_t), "wrong q8_k block size/padding");
|
||||
|
||||
|
||||
// Quantization
|
||||
void quantize_row_q2_k_reference(const float * restrict x, block_q2_k * restrict y, int k);
|
||||
void quantize_row_q3_k_reference(const float * restrict x, block_q3_k * restrict y, int k);
|
||||
void quantize_row_q4_k_reference(const float * restrict x, block_q4_k * restrict y, int k);
|
||||
void quantize_row_q5_k_reference(const float * restrict x, block_q5_k * restrict y, int k);
|
||||
void quantize_row_q6_k_reference(const float * restrict x, block_q6_k * restrict y, int k);
|
||||
void quantize_row_q8_k_reference(const float * restrict x, block_q8_k * restrict y, int k);
|
||||
|
||||
void quantize_row_q2_k(const float * restrict x, void * restrict y, int k);
|
||||
void quantize_row_q3_k(const float * restrict x, void * restrict y, int k);
|
||||
void quantize_row_q4_k(const float * restrict x, void * restrict y, int k);
|
||||
void quantize_row_q5_k(const float * restrict x, void * restrict y, int k);
|
||||
void quantize_row_q6_k(const float * restrict x, void * restrict y, int k);
|
||||
void quantize_row_q8_k(const float * restrict x, void * restrict y, int k);
|
||||
|
||||
// Dequantization
|
||||
void dequantize_row_q2_k(const block_q2_k * restrict x, float * restrict y, int k);
|
||||
void dequantize_row_q3_k(const block_q3_k * restrict x, float * restrict y, int k);
|
||||
void dequantize_row_q4_k(const block_q4_k * restrict x, float * restrict y, int k);
|
||||
void dequantize_row_q5_k(const block_q5_k * restrict x, float * restrict y, int k);
|
||||
void dequantize_row_q6_k(const block_q6_k * restrict x, float * restrict y, int k);
|
||||
void dequantize_row_q8_k(const block_q8_k * restrict x, float * restrict y, int k);
|
||||
|
||||
// Dot product
|
||||
void ggml_vec_dot_q2_k_q8_k(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
|
||||
void ggml_vec_dot_q3_k_q8_k(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
|
||||
void ggml_vec_dot_q4_k_q8_k(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
|
||||
void ggml_vec_dot_q5_k_q8_k(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
|
||||
void ggml_vec_dot_q6_k_q8_k(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
|
||||
|
||||
// Quantization with histogram collection
|
||||
size_t ggml_quantize_q2_k(const float * src, void * dst, int n, int k, int64_t * hist);
|
||||
size_t ggml_quantize_q3_k(const float * src, void * dst, int n, int k, int64_t * hist);
|
||||
size_t ggml_quantize_q4_k(const float * src, void * dst, int n, int k, int64_t * hist);
|
||||
size_t ggml_quantize_q5_k(const float * src, void * dst, int n, int k, int64_t * hist);
|
||||
size_t ggml_quantize_q6_k(const float * src, void * dst, int n, int k, int64_t * hist);
|
||||
|
||||
26
ggml.h
26
ggml.h
|
|
@ -241,6 +241,13 @@ extern "C" {
|
|||
GGML_TYPE_Q5_1 = 7,
|
||||
GGML_TYPE_Q8_0 = 8,
|
||||
GGML_TYPE_Q8_1 = 9,
|
||||
// k-quantizations
|
||||
GGML_TYPE_Q2_K = 10,
|
||||
GGML_TYPE_Q3_K = 11,
|
||||
GGML_TYPE_Q4_K = 12,
|
||||
GGML_TYPE_Q5_K = 13,
|
||||
GGML_TYPE_Q6_K = 14,
|
||||
GGML_TYPE_Q8_K = 15,
|
||||
GGML_TYPE_I8,
|
||||
GGML_TYPE_I16,
|
||||
GGML_TYPE_I32,
|
||||
|
|
@ -264,6 +271,11 @@ extern "C" {
|
|||
GGML_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q2_K = 10, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q3_K = 11, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q4_K = 12, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q5_K = 13, // except 1d tensors
|
||||
GGML_FTYPE_MOSTLY_Q6_K = 14, // except 1d tensors
|
||||
};
|
||||
|
||||
// available tensor operations:
|
||||
|
|
@ -425,6 +437,7 @@ extern "C" {
|
|||
GGML_API void ggml_print_objects(const struct ggml_context * ctx);
|
||||
|
||||
GGML_API int64_t ggml_nelements(const struct ggml_tensor * tensor);
|
||||
GGML_API int64_t ggml_nrows (const struct ggml_tensor * tensor);
|
||||
GGML_API size_t ggml_nbytes (const struct ggml_tensor * tensor);
|
||||
|
||||
GGML_API int ggml_blck_size (enum ggml_type type);
|
||||
|
|
@ -441,6 +454,9 @@ extern "C" {
|
|||
// TODO: temporary until model loading of ggml examples is refactored
|
||||
GGML_API enum ggml_type ggml_ftype_to_ggml_type(enum ggml_ftype ftype);
|
||||
|
||||
GGML_API bool ggml_is_transposed(const struct ggml_tensor * tensor);
|
||||
GGML_API bool ggml_is_contiguous(const struct ggml_tensor * tensor);
|
||||
|
||||
// use this to compute the memory overhead of a tensor
|
||||
GGML_API size_t ggml_tensor_overhead(void);
|
||||
|
||||
|
|
@ -454,6 +470,9 @@ extern "C" {
|
|||
GGML_API size_t ggml_set_scratch (struct ggml_context * ctx, struct ggml_scratch scratch);
|
||||
GGML_API void ggml_set_no_alloc(struct ggml_context * ctx, bool no_alloc);
|
||||
|
||||
GGML_API void * ggml_get_mem_buffer(struct ggml_context * ctx);
|
||||
GGML_API size_t ggml_get_mem_size (struct ggml_context * ctx);
|
||||
|
||||
GGML_API struct ggml_tensor * ggml_new_tensor(
|
||||
struct ggml_context * ctx,
|
||||
enum ggml_type type,
|
||||
|
|
@ -492,6 +511,8 @@ extern "C" {
|
|||
GGML_API struct ggml_tensor * ggml_dup_tensor (struct ggml_context * ctx, const struct ggml_tensor * src);
|
||||
GGML_API struct ggml_tensor * ggml_view_tensor(struct ggml_context * ctx, const struct ggml_tensor * src);
|
||||
|
||||
GGML_API struct ggml_tensor * ggml_get_tensor(struct ggml_context * ctx, const char * name);
|
||||
|
||||
GGML_API struct ggml_tensor * ggml_set_zero(struct ggml_tensor * tensor);
|
||||
GGML_API struct ggml_tensor * ggml_set_i32 (struct ggml_tensor * tensor, int32_t value);
|
||||
GGML_API struct ggml_tensor * ggml_set_f32 (struct ggml_tensor * tensor, float value);
|
||||
|
|
@ -978,7 +999,10 @@ extern "C" {
|
|||
GGML_API void ggml_graph_compute(struct ggml_context * ctx, struct ggml_cgraph * cgraph);
|
||||
GGML_API void ggml_graph_reset (struct ggml_cgraph * cgraph);
|
||||
|
||||
GGML_API struct ggml_tensor * ggml_get_tensor_by_name(struct ggml_cgraph * cgraph, const char * name);
|
||||
GGML_API struct ggml_tensor * ggml_graph_get_tensor(struct ggml_cgraph * cgraph, const char * name);
|
||||
|
||||
GGML_API void ggml_graph_export(const struct ggml_cgraph * cgraph, const char * fname);
|
||||
GGML_API struct ggml_cgraph ggml_graph_import(const char * fname, struct ggml_context ** ctx_data, struct ggml_context ** ctx_eval);
|
||||
|
||||
// print info and performance information for the graph
|
||||
GGML_API void ggml_graph_print(const struct ggml_cgraph * cgraph);
|
||||
|
|
|
|||
16
llama-util.h
16
llama-util.h
|
|
@ -405,13 +405,29 @@ struct llama_buffer {
|
|||
llama_buffer() = default;
|
||||
|
||||
void resize(size_t len) {
|
||||
#ifdef GGML_USE_METAL
|
||||
free(addr);
|
||||
int result = posix_memalign((void **) &addr, getpagesize(), len);
|
||||
if (result == 0) {
|
||||
memset(addr, 0, len);
|
||||
}
|
||||
else {
|
||||
addr = NULL;
|
||||
}
|
||||
#else
|
||||
delete[] addr;
|
||||
addr = new uint8_t[len];
|
||||
#endif
|
||||
size = len;
|
||||
}
|
||||
|
||||
~llama_buffer() {
|
||||
#ifdef GGML_USE_METAL
|
||||
free(addr);
|
||||
#else
|
||||
delete[] addr;
|
||||
#endif
|
||||
addr = NULL;
|
||||
}
|
||||
|
||||
// disable copy and move
|
||||
|
|
|
|||
315
llama.cpp
315
llama.cpp
|
|
@ -16,6 +16,10 @@
|
|||
#include "ggml-opencl.h"
|
||||
#endif
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
#include "ggml-metal.h"
|
||||
#endif
|
||||
|
||||
#include <array>
|
||||
#include <ctime>
|
||||
#include <cinttypes>
|
||||
|
|
@ -42,13 +46,13 @@
|
|||
// available llama models
|
||||
enum e_model {
|
||||
MODEL_UNKNOWN,
|
||||
MODEL_3B,
|
||||
MODEL_7B,
|
||||
MODEL_13B,
|
||||
MODEL_30B,
|
||||
MODEL_65B,
|
||||
};
|
||||
|
||||
|
||||
static const size_t MB = 1024*1024;
|
||||
|
||||
// computed for n_ctx == 2048
|
||||
|
|
@ -58,6 +62,7 @@ static const size_t MB = 1024*1024;
|
|||
static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
|
||||
{
|
||||
static std::map<e_model, size_t> k_sizes = {
|
||||
{ MODEL_3B, 256ull * MB },
|
||||
{ MODEL_7B, 512ull * MB },
|
||||
{ MODEL_13B, 512ull * MB },
|
||||
{ MODEL_30B, 512ull * MB },
|
||||
|
|
@ -69,6 +74,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
|
|||
static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
|
||||
{
|
||||
static std::map<e_model, size_t> k_sizes = {
|
||||
{ MODEL_3B, 256ull * MB },
|
||||
{ MODEL_7B, 512ull * MB },
|
||||
{ MODEL_13B, 512ull * MB },
|
||||
{ MODEL_30B, 512ull * MB },
|
||||
|
|
@ -81,6 +87,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
|
|||
static const std::map<e_model, size_t> & MEM_REQ_KV_SELF()
|
||||
{
|
||||
static std::map<e_model, size_t> k_sizes = {
|
||||
{ MODEL_3B, 682ull * MB },
|
||||
{ MODEL_7B, 1026ull * MB },
|
||||
{ MODEL_13B, 1608ull * MB },
|
||||
{ MODEL_30B, 3124ull * MB },
|
||||
|
|
@ -94,6 +101,7 @@ static const std::map<e_model, size_t> & MEM_REQ_KV_SELF()
|
|||
static const std::map<e_model, size_t> & MEM_REQ_EVAL()
|
||||
{
|
||||
static std::map<e_model, size_t> k_sizes = {
|
||||
{ MODEL_3B, 512ull * MB },
|
||||
{ MODEL_7B, 768ull * MB },
|
||||
{ MODEL_13B, 1024ull * MB },
|
||||
{ MODEL_30B, 1280ull * MB },
|
||||
|
|
@ -238,6 +246,10 @@ struct llama_context {
|
|||
llama_ctx_buffer buf_compute;
|
||||
llama_ctx_buffer buf_scratch[LLAMA_MAX_SCRATCH_BUFFERS];
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
ggml_metal_context * ctx_metal = NULL;
|
||||
#endif
|
||||
|
||||
int buf_last = 0;
|
||||
size_t buf_max_size[LLAMA_MAX_SCRATCH_BUFFERS] = { 0 };
|
||||
|
||||
|
|
@ -277,15 +289,15 @@ template <typename T>
|
|||
static T checked_mul(T a, T b) {
|
||||
T ret = a * b;
|
||||
if (a != 0 && ret / a != b) {
|
||||
throw format("overflow multiplying %llu * %llu",
|
||||
(unsigned long long) a, (unsigned long long) b);
|
||||
throw std::runtime_error(format("overflow multiplying %llu * %llu",
|
||||
(unsigned long long) a, (unsigned long long) b));
|
||||
}
|
||||
return ret;
|
||||
}
|
||||
|
||||
static size_t checked_div(size_t a, size_t b) {
|
||||
if (b == 0 || a % b != 0) {
|
||||
throw format("error dividing %zu / %zu", a, b);
|
||||
throw std::runtime_error(format("error dividing %zu / %zu", a, b));
|
||||
}
|
||||
return a / b;
|
||||
}
|
||||
|
|
@ -349,7 +361,7 @@ struct llama_load_tensor {
|
|||
const auto & first_shard = shards.at(0);
|
||||
for (const auto & shard : shards) {
|
||||
if (shard.type != first_shard.type) {
|
||||
throw format("inconsistent tensor shard type in '%s'", name.c_str());
|
||||
throw std::runtime_error(format("inconsistent tensor shard type in '%s'", name.c_str()));
|
||||
}
|
||||
}
|
||||
type = first_shard.type;
|
||||
|
|
@ -372,8 +384,8 @@ struct llama_load_tensor {
|
|||
const auto & first_shard = shards.at(0);
|
||||
for (const auto & shard : shards) {
|
||||
if (shard.ne != first_shard.ne) {
|
||||
throw format("inconsistent tensor shard shape in '%s': first was %s, other was %s",
|
||||
name.c_str(), llama_format_tensor_shape(first_shard.ne).c_str(), llama_format_tensor_shape(shard.ne).c_str());
|
||||
throw std::runtime_error(format("inconsistent tensor shard shape in '%s': first was %s, other was %s",
|
||||
name.c_str(), llama_format_tensor_shape(first_shard.ne).c_str(), llama_format_tensor_shape(shard.ne).c_str()));
|
||||
}
|
||||
}
|
||||
ne = first_shard.ne;
|
||||
|
|
@ -451,8 +463,8 @@ struct llama_file_loader {
|
|||
}
|
||||
}
|
||||
|
||||
throw format("unknown (magic, version) combination: %08x, %08x; is this really a GGML file?",
|
||||
magic, version);
|
||||
throw std::runtime_error(format("unknown (magic, version) combination: %08x, %08x; is this really a GGML file?",
|
||||
magic, version));
|
||||
}
|
||||
void read_hparams() {
|
||||
hparams.n_vocab = file.read_u32();
|
||||
|
|
@ -492,7 +504,7 @@ struct llama_file_loader {
|
|||
file.read_raw(shard.ne.data(), sizeof(shard.ne[0]) * n_dims);
|
||||
std::string name = file.read_string(name_len);
|
||||
if (n_dims < 1 || n_dims > 2) {
|
||||
throw format("llama.cpp: tensor '%s' should not be %u-dimensional", name.c_str(), n_dims);
|
||||
throw std::runtime_error(format("llama.cpp: tensor '%s' should not be %u-dimensional", name.c_str(), n_dims));
|
||||
}
|
||||
switch (shard.type) {
|
||||
case GGML_TYPE_F32:
|
||||
|
|
@ -502,9 +514,14 @@ struct llama_file_loader {
|
|||
case GGML_TYPE_Q5_0:
|
||||
case GGML_TYPE_Q5_1:
|
||||
case GGML_TYPE_Q8_0:
|
||||
case GGML_TYPE_Q2_K:
|
||||
case GGML_TYPE_Q3_K:
|
||||
case GGML_TYPE_Q4_K:
|
||||
case GGML_TYPE_Q5_K:
|
||||
case GGML_TYPE_Q6_K:
|
||||
break;
|
||||
default: {
|
||||
throw format("unrecognized tensor type %u\n", shard.type);
|
||||
throw std::runtime_error(format("unrecognized tensor type %u\n", shard.type));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -577,6 +594,11 @@ struct llama_file_saver {
|
|||
case GGML_TYPE_Q5_0:
|
||||
case GGML_TYPE_Q5_1:
|
||||
case GGML_TYPE_Q8_0:
|
||||
case GGML_TYPE_Q2_K:
|
||||
case GGML_TYPE_Q3_K:
|
||||
case GGML_TYPE_Q4_K:
|
||||
case GGML_TYPE_Q5_K:
|
||||
case GGML_TYPE_Q6_K:
|
||||
break;
|
||||
default: LLAMA_ASSERT(false);
|
||||
}
|
||||
|
|
@ -608,7 +630,7 @@ struct llama_model_loader {
|
|||
auto * ith_file = new llama_file_loader(fname.c_str(), i, tensors_map);
|
||||
file_loaders.emplace_back(ith_file);
|
||||
if (ith_file->hparams != first_file->hparams) {
|
||||
throw format("llama.cpp: hparams inconsistent between files");
|
||||
throw std::runtime_error(format("llama.cpp: hparams inconsistent between files"));
|
||||
}
|
||||
}
|
||||
if (!llama_mmap::SUPPORTED) {
|
||||
|
|
@ -638,7 +660,7 @@ struct llama_model_loader {
|
|||
uint32_t guess_n_parts() const {
|
||||
auto it = tensors_map.name_to_idx.find("tok_embeddings.weight");
|
||||
if (it == tensors_map.name_to_idx.end()) {
|
||||
throw std::string("missing tok_embeddings.weight");
|
||||
throw std::runtime_error(std::string("missing tok_embeddings.weight"));
|
||||
}
|
||||
const llama_load_tensor & lt = tensors_map.tensors.at(it->second);
|
||||
return file_loaders.at(0)->hparams.n_embd / lt.shards.at(0).ne.at(0);
|
||||
|
|
@ -655,12 +677,12 @@ struct llama_model_loader {
|
|||
struct ggml_tensor * get_tensor(const std::string & name, const std::vector<uint32_t> & ne, ggml_backend backend) {
|
||||
auto it = tensors_map.name_to_idx.find(name);
|
||||
if (it == tensors_map.name_to_idx.end()) {
|
||||
throw format("llama.cpp: tensor '%s' is missing from model", name.c_str());
|
||||
throw std::runtime_error(std::runtime_error(format("llama.cpp: tensor '%s' is missing from model", name.c_str())));
|
||||
}
|
||||
llama_load_tensor & lt = tensors_map.tensors.at(it->second);
|
||||
if (lt.ne != ne) {
|
||||
throw format("llama.cpp: tensor '%s' has wrong shape; expected %s, got %s",
|
||||
name.c_str(), llama_format_tensor_shape(ne).c_str(), llama_format_tensor_shape(lt.ne).c_str());
|
||||
throw std::runtime_error(format("llama.cpp: tensor '%s' has wrong shape; expected %s, got %s",
|
||||
name.c_str(), llama_format_tensor_shape(ne).c_str(), llama_format_tensor_shape(lt.ne).c_str()));
|
||||
}
|
||||
|
||||
return get_tensor_for(lt, backend);
|
||||
|
|
@ -684,7 +706,7 @@ struct llama_model_loader {
|
|||
|
||||
void done_getting_tensors() const {
|
||||
if (num_ggml_tensors_created != tensors_map.tensors.size()) {
|
||||
throw std::string("llama.cpp: file contained more tensors than expected");
|
||||
throw std::runtime_error(std::string("llama.cpp: file contained more tensors than expected"));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -893,12 +915,23 @@ static const char *llama_ftype_name(enum llama_ftype ftype) {
|
|||
case LLAMA_FTYPE_MOSTLY_Q5_0: return "mostly Q5_0";
|
||||
case LLAMA_FTYPE_MOSTLY_Q5_1: return "mostly Q5_1";
|
||||
case LLAMA_FTYPE_MOSTLY_Q8_0: return "mostly Q8_0";
|
||||
// K-quants
|
||||
case LLAMA_FTYPE_MOSTLY_Q2_K: return "mostly Q2_K";
|
||||
case LLAMA_FTYPE_MOSTLY_Q3_K_S: return "mostly Q3_K - Small";
|
||||
case LLAMA_FTYPE_MOSTLY_Q3_K_M: return "mostly Q3_K - Medium";
|
||||
case LLAMA_FTYPE_MOSTLY_Q3_K_L: return "mostly Q3_K - Large";
|
||||
case LLAMA_FTYPE_MOSTLY_Q4_K_S: return "mostly Q4_K - Small";
|
||||
case LLAMA_FTYPE_MOSTLY_Q4_K_M: return "mostly Q4_K - Medium";
|
||||
case LLAMA_FTYPE_MOSTLY_Q5_K_S: return "mostly Q5_K - Small";
|
||||
case LLAMA_FTYPE_MOSTLY_Q5_K_M: return "mostly Q5_K - Medium";
|
||||
case LLAMA_FTYPE_MOSTLY_Q6_K: return "mostly Q6_K";
|
||||
default: return "unknown, may not work";
|
||||
}
|
||||
}
|
||||
|
||||
static const char *llama_model_type_name(e_model type) {
|
||||
switch (type) {
|
||||
case MODEL_3B: return "3B";
|
||||
case MODEL_7B: return "7B";
|
||||
case MODEL_13B: return "13B";
|
||||
case MODEL_30B: return "30B";
|
||||
|
|
@ -932,6 +965,7 @@ static void llama_model_load_internal(
|
|||
|
||||
{
|
||||
switch (hparams.n_layer) {
|
||||
case 26: model.type = e_model::MODEL_3B; break;
|
||||
case 32: model.type = e_model::MODEL_7B; break;
|
||||
case 40: model.type = e_model::MODEL_13B; break;
|
||||
case 60: model.type = e_model::MODEL_30B; break;
|
||||
|
|
@ -960,7 +994,7 @@ static void llama_model_load_internal(
|
|||
if (hparams.ftype != LLAMA_FTYPE_ALL_F32 &&
|
||||
hparams.ftype != LLAMA_FTYPE_MOSTLY_F16 &&
|
||||
hparams.ftype != LLAMA_FTYPE_MOSTLY_Q8_0) {
|
||||
throw format("this format is no longer supported (see https://github.com/ggerganov/llama.cpp/pull/1405)");
|
||||
throw std::runtime_error(format("this format is no longer supported (see https://github.com/ggerganov/llama.cpp/pull/1405)"));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -968,7 +1002,7 @@ static void llama_model_load_internal(
|
|||
if (hparams.ftype == LLAMA_FTYPE_MOSTLY_Q4_0 ||
|
||||
hparams.ftype == LLAMA_FTYPE_MOSTLY_Q4_1 ||
|
||||
hparams.ftype == LLAMA_FTYPE_MOSTLY_Q8_0) {
|
||||
throw format("this format is no longer supported (see https://github.com/ggerganov/llama.cpp/pull/1508)");
|
||||
throw std::runtime_error(format("this format is no longer supported (see https://github.com/ggerganov/llama.cpp/pull/1508)"));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -999,12 +1033,16 @@ static void llama_model_load_internal(
|
|||
|
||||
model.ctx = ggml_init(params);
|
||||
if (!model.ctx) {
|
||||
throw format("ggml_init() failed");
|
||||
throw std::runtime_error(format("ggml_init() failed"));
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
#if defined(GGML_USE_CUBLAS)
|
||||
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CUDA
|
||||
fprintf(stderr, "%s: using CUDA for GPU acceleration\n", __func__);
|
||||
#elif defined(GGML_USE_CLBLAST)
|
||||
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CL
|
||||
fprintf(stderr, "%s: using OpenCL for GPU acceleration\n", __func__);
|
||||
#else
|
||||
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CPU
|
||||
#endif
|
||||
|
|
@ -1056,7 +1094,7 @@ static void llama_model_load_internal(
|
|||
layer.w2 = ml->get_tensor(layers_i + ".feed_forward.w2.weight", { n_ff, n_embd}, backend);
|
||||
layer.w3 = ml->get_tensor(layers_i + ".feed_forward.w3.weight", {n_embd, n_ff}, backend);
|
||||
|
||||
if (backend == GGML_BACKEND_CUDA) {
|
||||
if (backend == LLAMA_BACKEND_OFFLOAD) {
|
||||
vram_total +=
|
||||
ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk) +
|
||||
ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.attention_norm) +
|
||||
|
|
@ -1086,15 +1124,15 @@ static void llama_model_load_internal(
|
|||
fprintf(stderr, "%s: mem required = %7.2f MB (+ %7.2f MB per state)\n", __func__,
|
||||
mem_required / 1024.0 / 1024.0, mem_required_state / 1024.0 / 1024.0);
|
||||
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
|
||||
|
||||
fprintf(stderr, "%s: [cublas] offloading %d layers to GPU\n", __func__, n_gpu);
|
||||
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_CLBLAST)
|
||||
fprintf(stderr, "%s: offloading %d layers to GPU\n", __func__, n_gpu);
|
||||
if (n_gpu_layers > (int) hparams.n_layer) {
|
||||
fprintf(stderr, "%s: [cublas] offloading output layer to GPU\n", __func__);
|
||||
fprintf(stderr, "%s: offloading output layer to GPU\n", __func__);
|
||||
}
|
||||
fprintf(stderr, "%s: [cublas] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
|
||||
#elif !defined(GGML_USE_CLBLAST)
|
||||
fprintf(stderr, "%s: total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
|
||||
#else
|
||||
(void) n_gpu_layers;
|
||||
#endif
|
||||
}
|
||||
|
|
@ -1106,7 +1144,7 @@ static void llama_model_load_internal(
|
|||
|
||||
ml->load_all_data(progress_callback, progress_callback_user_data, use_mlock ? &lctx.model.mlock_mmap : NULL);
|
||||
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
#if defined(GGML_USE_CUBLAS)
|
||||
{
|
||||
size_t done_size = 0;
|
||||
size_t data_size = 0;
|
||||
|
|
@ -1129,29 +1167,24 @@ static void llama_model_load_internal(
|
|||
}
|
||||
#elif defined(GGML_USE_CLBLAST)
|
||||
{
|
||||
const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
|
||||
|
||||
fprintf(stderr, "ggml_opencl: offloading %d layers to GPU\n", n_gpu);
|
||||
|
||||
size_t vram_total = 0;
|
||||
|
||||
for (int i = 0; i < n_gpu; ++i) {
|
||||
const auto & layer = model.layers[i];
|
||||
|
||||
ggml_cl_transform_tensor(layer.wq); vram_total += ggml_nbytes(layer.wq);
|
||||
ggml_cl_transform_tensor(layer.wk); vram_total += ggml_nbytes(layer.wk);
|
||||
ggml_cl_transform_tensor(layer.wv); vram_total += ggml_nbytes(layer.wv);
|
||||
ggml_cl_transform_tensor(layer.wo); vram_total += ggml_nbytes(layer.wo);
|
||||
ggml_cl_transform_tensor(layer.w1); vram_total += ggml_nbytes(layer.w1);
|
||||
ggml_cl_transform_tensor(layer.w2); vram_total += ggml_nbytes(layer.w2);
|
||||
ggml_cl_transform_tensor(layer.w3); vram_total += ggml_nbytes(layer.w3);
|
||||
size_t done_size = 0;
|
||||
size_t data_size = 0;
|
||||
for (llama_load_tensor & lt : ml->tensors_map.tensors) {
|
||||
data_size += lt.size;
|
||||
if (lt.ggml_tensor->backend == GGML_BACKEND_CPU) {
|
||||
done_size += lt.size;
|
||||
}
|
||||
if (n_gpu_layers > (int) hparams.n_layer) {
|
||||
fprintf(stderr, "ggml_opencl: offloading output layer to GPU\n");
|
||||
ggml_cl_transform_tensor(model.output); vram_total += ggml_nbytes(model.output);
|
||||
}
|
||||
|
||||
fprintf(stderr, "ggml_opencl: total VRAM used: %zu MB\n", vram_total / 1024 / 1024);
|
||||
for (llama_load_tensor & lt : ml->tensors_map.tensors) {
|
||||
if (lt.ggml_tensor->backend != GGML_BACKEND_CL) {
|
||||
continue;
|
||||
}
|
||||
if (progress_callback) {
|
||||
progress_callback((float) done_size / data_size, progress_callback_user_data);
|
||||
}
|
||||
ggml_cl_load_data(fname.c_str(), lt.ggml_tensor, lt.shards.at(0).file_off);
|
||||
done_size += lt.size;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
|
|
@ -1181,8 +1214,8 @@ static bool llama_model_load(
|
|||
llama_model_load_internal(fname, lctx, n_ctx, n_gpu_layers, memory_type, use_mmap, use_mlock,
|
||||
vocab_only, progress_callback, progress_callback_user_data);
|
||||
return true;
|
||||
} catch (const std::string & err) {
|
||||
fprintf(stderr, "error loading model: %s\n", err.c_str());
|
||||
} catch (const std::exception & err) {
|
||||
fprintf(stderr, "error loading model: %s\n", err.what());
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
|
@ -1193,13 +1226,15 @@ static bool llama_model_load(
|
|||
// - tokens: new batch of tokens to process
|
||||
// - n_past: the context size so far
|
||||
// - n_threads: number of threads to use
|
||||
// - cgraph_fname: filename of the exported computation graph
|
||||
//
|
||||
static bool llama_eval_internal(
|
||||
llama_context & lctx,
|
||||
const llama_token * tokens,
|
||||
const int n_tokens,
|
||||
const int n_past,
|
||||
const int n_threads) {
|
||||
const int n_threads,
|
||||
const char * cgraph_fname) {
|
||||
|
||||
// enforce that the first token is BOS
|
||||
if (n_past == 0 && tokens[0] != llama_token_bos()) {
|
||||
|
|
@ -1245,13 +1280,12 @@ static bool llama_eval_internal(
|
|||
ggml_set_name(embd, "embd");
|
||||
memcpy(embd->data, tokens, N*ggml_element_size(embd));
|
||||
|
||||
struct ggml_tensor * cur;
|
||||
struct ggml_tensor * inpL = ggml_get_rows(ctx0, model.tok_embeddings, embd);
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
struct ggml_tensor * inpSA = inpL;
|
||||
|
||||
struct ggml_tensor * cur;
|
||||
|
||||
lctx.use_buf(ctx0, 0);
|
||||
|
||||
// norm
|
||||
|
|
@ -1265,6 +1299,7 @@ static bool llama_eval_internal(
|
|||
// self-attention
|
||||
{
|
||||
// compute Q and K and RoPE them
|
||||
|
||||
struct ggml_tensor * Qcur = ggml_rope_inplace(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wq, cur), n_embd/n_head, n_head, N), n_past, n_rot, 0);
|
||||
struct ggml_tensor * Kcur = ggml_rope_inplace(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wk, cur), n_embd/n_head, n_head, N), n_past, n_rot, 0);
|
||||
ggml_set_name(Qcur, "Qcur");
|
||||
|
|
@ -1274,6 +1309,7 @@ static bool llama_eval_internal(
|
|||
{
|
||||
// compute the transposed [N, n_embd] V matrix
|
||||
struct ggml_tensor * Vcur = ggml_transpose(ctx0, ggml_reshape_2d(ctx0, ggml_mul_mat(ctx0, model.layers[il].wv, cur), n_embd, N));
|
||||
ggml_set_name(Vcur, "Vcur");
|
||||
|
||||
struct ggml_tensor * k = ggml_view_1d(ctx0, kv_self.k, N*n_embd, (ggml_element_size(kv_self.k)*n_embd)*(il*n_ctx + n_past));
|
||||
struct ggml_tensor * v = ggml_view_2d(ctx0, kv_self.v, N, n_embd,
|
||||
|
|
@ -1319,7 +1355,6 @@ static bool llama_eval_internal(
|
|||
struct ggml_tensor * KQ_soft_max = ggml_soft_max_inplace(ctx0, KQ_masked);
|
||||
ggml_set_name(KQ_soft_max, "KQ_soft_max");
|
||||
|
||||
|
||||
// split cached V into n_head heads
|
||||
struct ggml_tensor * V =
|
||||
ggml_view_3d(ctx0, kv_self.v,
|
||||
|
|
@ -1401,26 +1436,55 @@ static bool llama_eval_internal(
|
|||
|
||||
// norm
|
||||
{
|
||||
cur = ggml_rms_norm(ctx0, inpL);
|
||||
|
||||
inpL = ggml_rms_norm(ctx0, inpL);
|
||||
// cur = cur*norm(broadcasted)
|
||||
cur = ggml_mul(ctx0, cur, model.norm);
|
||||
|
||||
// inpL = inpL*norm(broadcasted)
|
||||
inpL = ggml_mul(ctx0, inpL, model.norm);
|
||||
|
||||
embeddings = inpL;
|
||||
embeddings = cur;
|
||||
}
|
||||
|
||||
// lm_head
|
||||
inpL = ggml_mul_mat(ctx0, model.output, inpL);
|
||||
cur = ggml_mul_mat(ctx0, model.output, cur);
|
||||
|
||||
lctx.use_buf(ctx0, -1);
|
||||
|
||||
// logits -> probs
|
||||
//inpL = ggml_soft_max_inplace(ctx0, inpL);
|
||||
//cur = ggml_soft_max_inplace(ctx0, cur);
|
||||
|
||||
// run the computation
|
||||
ggml_build_forward_expand(&gf, inpL);
|
||||
ggml_build_forward_expand(&gf, cur);
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
if (lctx.ctx_metal && N == 1) {
|
||||
ggml_metal_graph_compute(lctx.ctx_metal, &gf);
|
||||
ggml_metal_get_tensor (lctx.ctx_metal, cur);
|
||||
} else {
|
||||
// IMPORTANT:
|
||||
// Since we don't have efficient Matrix x Matrix Metal multiplication yet, we fallback to vanilla
|
||||
// ggml_graph_compute(). It uses Apple's Accelerate CBLAS API which takes advantage of the ANE or the AMX
|
||||
// coprocessor.
|
||||
//
|
||||
// When we implement Matrix x Matrix Metal multiplication, we can avoid this branch.
|
||||
// But for now, we have focused only on Matrix x Vector Metal multiplication.
|
||||
//
|
||||
// TODO: avoid these syncs via shared memory (ref #1696)
|
||||
//
|
||||
if (lctx.ctx_metal) {
|
||||
// We need to sync the GPU KV cache with the CPU KV cache
|
||||
ggml_metal_get_tensor(lctx.ctx_metal, kv_self.k);
|
||||
ggml_metal_get_tensor(lctx.ctx_metal, kv_self.v);
|
||||
}
|
||||
|
||||
ggml_graph_compute(ctx0, &gf);
|
||||
}
|
||||
#else
|
||||
ggml_graph_compute(ctx0, &gf);
|
||||
#endif
|
||||
|
||||
if (cgraph_fname) {
|
||||
ggml_graph_export(&gf, cgraph_fname);
|
||||
}
|
||||
|
||||
#ifdef GGML_PERF
|
||||
// print timing information per ggml operation (for debugging purposes)
|
||||
|
|
@ -1434,7 +1498,7 @@ static bool llama_eval_internal(
|
|||
//}
|
||||
|
||||
//embd_w.resize(n_vocab*N);
|
||||
//memcpy(embd_w.data(), ggml_get_data(inpL), sizeof(float)*n_vocab*N);
|
||||
//memcpy(embd_w.data(), ggml_get_data(cur), sizeof(float)*n_vocab*N);
|
||||
|
||||
// update kv token count
|
||||
lctx.model.kv_self.n = n_past + N;
|
||||
|
|
@ -1445,11 +1509,11 @@ static bool llama_eval_internal(
|
|||
|
||||
if (lctx.logits_all) {
|
||||
logits_out.resize(n_vocab * N);
|
||||
memcpy(logits_out.data(), (float *) ggml_get_data(inpL), sizeof(float)*n_vocab*N);
|
||||
memcpy(logits_out.data(), (float *) ggml_get_data(cur), sizeof(float)*n_vocab*N);
|
||||
} else {
|
||||
// return result for just the last token
|
||||
logits_out.resize(n_vocab);
|
||||
memcpy(logits_out.data(), (float *) ggml_get_data(inpL) + (n_vocab*(N-1)), sizeof(float)*n_vocab);
|
||||
memcpy(logits_out.data(), (float *) ggml_get_data(cur) + (n_vocab*(N-1)), sizeof(float)*n_vocab);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -2056,8 +2120,19 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
case LLAMA_FTYPE_MOSTLY_Q5_0: quantized_type = GGML_TYPE_Q5_0; break;
|
||||
case LLAMA_FTYPE_MOSTLY_Q5_1: quantized_type = GGML_TYPE_Q5_1; break;
|
||||
case LLAMA_FTYPE_MOSTLY_Q8_0: quantized_type = GGML_TYPE_Q8_0; break;
|
||||
default: throw format("invalid output file type %d\n", ftype);
|
||||
};
|
||||
|
||||
// K-quants
|
||||
case LLAMA_FTYPE_MOSTLY_Q2_K: quantized_type = GGML_TYPE_Q2_K; break;
|
||||
case LLAMA_FTYPE_MOSTLY_Q3_K_S:
|
||||
case LLAMA_FTYPE_MOSTLY_Q3_K_M:
|
||||
case LLAMA_FTYPE_MOSTLY_Q3_K_L: quantized_type = GGML_TYPE_Q3_K; break;
|
||||
case LLAMA_FTYPE_MOSTLY_Q4_K_S:
|
||||
case LLAMA_FTYPE_MOSTLY_Q4_K_M: quantized_type = GGML_TYPE_Q4_K; break;
|
||||
case LLAMA_FTYPE_MOSTLY_Q5_K_S:
|
||||
case LLAMA_FTYPE_MOSTLY_Q5_K_M: quantized_type = GGML_TYPE_Q5_K; break;
|
||||
case LLAMA_FTYPE_MOSTLY_Q6_K: quantized_type = GGML_TYPE_Q6_K; break;
|
||||
default: throw std::runtime_error(format("invalid output file type %d\n", ftype));
|
||||
}
|
||||
|
||||
if (nthread <= 0) {
|
||||
nthread = std::thread::hardware_concurrency();
|
||||
|
|
@ -2067,6 +2142,20 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
/*vocab_only*/ false));
|
||||
llama_file_saver file_saver(fname_out.c_str(), model_loader->file_loaders.at(0).get(), ftype);
|
||||
|
||||
int n_attention_wv = 0;
|
||||
int n_feed_forward_w2 = 0;
|
||||
for (auto& tensor : model_loader->tensors_map.tensors) {
|
||||
if (tensor.name.find("attention.wv.weight") != std::string::npos) {
|
||||
++n_attention_wv;
|
||||
}
|
||||
else if (tensor.name.find("feed_forward.w2.weight") != std::string::npos) {
|
||||
++n_feed_forward_w2;
|
||||
}
|
||||
}
|
||||
|
||||
int i_attention_wv = 0;
|
||||
int i_feed_forward_w2 = 0;
|
||||
|
||||
size_t total_size_org = 0;
|
||||
size_t total_size_new = 0;
|
||||
std::vector<int64_t> hist_all(1 << 4, 0);
|
||||
|
|
@ -2109,6 +2198,32 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
printf("size = %8.3f MB\n", tensor.size/1024.0/1024.0);
|
||||
} else {
|
||||
new_type = quantized_type;
|
||||
// TODO: temporary disabled until Metal / OpenCL support is available
|
||||
// ref: https://github.com/ggerganov/llama.cpp/issues/1711
|
||||
//if (tensor.name == "output.weight") {
|
||||
// new_type = GGML_TYPE_Q6_K;
|
||||
//}
|
||||
if (tensor.name.find("attention.wv.weight") != std::string::npos) {
|
||||
if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
|
||||
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
|
||||
else if ((ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) &&
|
||||
(i_attention_wv < n_attention_wv/8 || i_attention_wv >= 7*n_attention_wv/8 ||
|
||||
(i_attention_wv - n_attention_wv/8)%3 == 2)) new_type = GGML_TYPE_Q6_K;
|
||||
++i_attention_wv;
|
||||
}
|
||||
if (tensor.name.find("feed_forward.w2.weight") != std::string::npos) {
|
||||
if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
|
||||
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
|
||||
else if ((ftype == LLAMA_FTYPE_MOSTLY_Q4_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q5_K_M) &&
|
||||
(i_feed_forward_w2 < n_feed_forward_w2/8 || i_feed_forward_w2 >= 7*n_feed_forward_w2/8 ||
|
||||
(i_feed_forward_w2 - n_feed_forward_w2/8)%3 == 2)) new_type = GGML_TYPE_Q6_K;
|
||||
++i_feed_forward_w2;
|
||||
}
|
||||
if (tensor.name.find("attention.wo.weight") != std::string::npos) {
|
||||
if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_M || ftype == LLAMA_FTYPE_MOSTLY_Q2_K) new_type = GGML_TYPE_Q4_K;
|
||||
else if (ftype == LLAMA_FTYPE_MOSTLY_Q3_K_L) new_type = GGML_TYPE_Q5_K;
|
||||
}
|
||||
|
||||
float * f32_data;
|
||||
size_t nelements = tensor.ne.at(0) * tensor.ne.at(1);
|
||||
llama_buffer f32_conv_buf;
|
||||
|
|
@ -2122,7 +2237,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
f32_data[i] = ggml_fp16_to_fp32(f16_data[i]);
|
||||
}
|
||||
} else {
|
||||
throw format("type %s unsupported for integer quantization", ggml_type_name(tensor.type));
|
||||
throw std::runtime_error(format("type %s unsupported for integer quantization", ggml_type_name(tensor.type)));
|
||||
}
|
||||
|
||||
printf("quantizing .. ");
|
||||
|
|
@ -2176,13 +2291,17 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
}
|
||||
|
||||
printf("size = %8.2f MB -> %8.2f MB | hist: ", tensor.size/1024.0/1024.0, new_size/1024.0/1024.0);
|
||||
int64_t tot_count = 0;
|
||||
for (size_t i = 0; i < hist_cur.size(); i++) {
|
||||
hist_all[i] += hist_cur[i];
|
||||
tot_count += hist_cur[i];
|
||||
}
|
||||
|
||||
if (tot_count > 0) {
|
||||
for (size_t i = 0; i < hist_cur.size(); i++) {
|
||||
printf("%5.3f ", hist_cur[i] / float(nelements));
|
||||
}
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
total_size_org += tensor.size;
|
||||
|
|
@ -2199,6 +2318,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
sum_all += hist_all[i];
|
||||
}
|
||||
|
||||
if (sum_all > 0) {
|
||||
printf("%s: hist: ", __func__);
|
||||
for (size_t i = 0; i < hist_all.size(); i++) {
|
||||
printf("%5.3f ", hist_all[i] / float(sum_all));
|
||||
|
|
@ -2206,6 +2326,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
|
|||
printf("\n");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
//
|
||||
// interface implementation
|
||||
|
|
@ -2284,6 +2405,38 @@ struct llama_context * llama_init_from_file(
|
|||
ctx->buf_scratch[1].resize(MEM_REQ_SCRATCH1().at(ctx->model.type));
|
||||
}
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
if (params.n_gpu_layers > 0) {
|
||||
// this allocates all Metal resources and memory buffers
|
||||
ctx->ctx_metal = ggml_metal_init();
|
||||
|
||||
void *data_ptr = NULL;
|
||||
size_t data_size = 0;
|
||||
if (params.use_mmap) {
|
||||
data_ptr = ctx->model.mapping->addr;
|
||||
data_size= ctx->model.mapping->size;
|
||||
} else {
|
||||
data_ptr = ggml_get_mem_buffer(ctx->model.ctx);
|
||||
data_size= ggml_get_mem_size(ctx->model.ctx);
|
||||
}
|
||||
|
||||
#define LLAMA_METAL_CHECK_BUF(result) \
|
||||
if (!(result)) { \
|
||||
fprintf(stderr, "%s: failed to add buffer\n", __func__); \
|
||||
llama_free(ctx); \
|
||||
return NULL; \
|
||||
}
|
||||
|
||||
LLAMA_METAL_CHECK_BUF(ggml_metal_add_buffer(ctx->ctx_metal, "data", data_ptr, data_size));
|
||||
LLAMA_METAL_CHECK_BUF(ggml_metal_add_buffer(ctx->ctx_metal, "eval", ctx->buf_compute.addr, ctx->buf_compute.size));
|
||||
|
||||
LLAMA_METAL_CHECK_BUF(ggml_metal_add_buffer(ctx->ctx_metal, "kv", ctx->model.kv_self.buf.addr, ctx->model.kv_self.buf.size));
|
||||
LLAMA_METAL_CHECK_BUF(ggml_metal_add_buffer(ctx->ctx_metal, "scr0", ctx->buf_scratch[0].addr, ctx->buf_scratch[0].size));
|
||||
LLAMA_METAL_CHECK_BUF(ggml_metal_add_buffer(ctx->ctx_metal, "scr1", ctx->buf_scratch[1].addr, ctx->buf_scratch[1].size));
|
||||
#undef LLAMA_METAL_CHECK_BUF
|
||||
}
|
||||
#endif
|
||||
|
||||
return ctx;
|
||||
}
|
||||
|
||||
|
|
@ -2299,8 +2452,8 @@ int llama_model_quantize(
|
|||
try {
|
||||
llama_model_quantize_internal(fname_inp, fname_out, ftype, nthread);
|
||||
return 0;
|
||||
} catch (const std::string & err) {
|
||||
fprintf(stderr, "%s: failed to quantize: %s\n", __func__, err.c_str());
|
||||
} catch (const std::exception & err) {
|
||||
fprintf(stderr, "%s: failed to quantize: %s\n", __func__, err.what());
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
|
@ -2553,8 +2706,8 @@ int llama_apply_lora_from_file_internal(struct llama_context * ctx, const char *
|
|||
int llama_apply_lora_from_file(struct llama_context * ctx, const char * path_lora, const char * path_base_model, int n_threads) {
|
||||
try {
|
||||
return llama_apply_lora_from_file_internal(ctx, path_lora, path_base_model, n_threads);
|
||||
} catch (const std::string & err) {
|
||||
fprintf(stderr, "%s: failed to apply lora adapter: %s\n", __func__, err.c_str());
|
||||
} catch (const std::exception & err) {
|
||||
fprintf(stderr, "%s: failed to apply lora adapter: %s\n", __func__, err.what());
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
|
@ -2899,7 +3052,7 @@ int llama_eval(
|
|||
int n_tokens,
|
||||
int n_past,
|
||||
int n_threads) {
|
||||
if (!llama_eval_internal(*ctx, tokens, n_tokens, n_past, n_threads)) {
|
||||
if (!llama_eval_internal(*ctx, tokens, n_tokens, n_past, n_threads, nullptr)) {
|
||||
fprintf(stderr, "%s: failed to eval\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
|
@ -2914,6 +3067,20 @@ int llama_eval(
|
|||
return 0;
|
||||
}
|
||||
|
||||
int llama_eval_export(struct llama_context * ctx, const char * fname) {
|
||||
const int n_batch = 1;
|
||||
const int n_ctx = 512 - n_batch;
|
||||
|
||||
const std::vector<llama_token> tmp(n_batch, llama_token_bos());
|
||||
|
||||
if (!llama_eval_internal(*ctx, tmp.data(), tmp.size(), n_ctx, 1, fname)) {
|
||||
fprintf(stderr, "%s: failed to eval\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
int llama_tokenize(
|
||||
struct llama_context * ctx,
|
||||
const char * text,
|
||||
|
|
|
|||
20
llama.h
20
llama.h
|
|
@ -31,6 +31,11 @@
|
|||
#define LLAMA_SESSION_MAGIC LLAMA_FILE_MAGIC_GGSN
|
||||
#define LLAMA_SESSION_VERSION 1
|
||||
|
||||
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_CLBLAST) || defined(GGML_USE_METAL)
|
||||
// Defined when llama.cpp is compiled with support for offloading model layers to GPU.
|
||||
#define LLAMA_SUPPORTS_GPU_OFFLOAD
|
||||
#endif
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
|
@ -89,6 +94,15 @@ extern "C" {
|
|||
LLAMA_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q2_K = 10,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q3_K_S = 11,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q3_K_M = 12,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q3_K_L = 13,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q4_K_S = 14,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q4_K_M = 15,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q5_K_S = 16,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q5_K_M = 17,// except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q6_K = 18,// except 1d tensors
|
||||
};
|
||||
|
||||
LLAMA_API struct llama_context_params llama_context_default_params();
|
||||
|
|
@ -168,6 +182,12 @@ extern "C" {
|
|||
int n_past,
|
||||
int n_threads);
|
||||
|
||||
// Export a static computation graph for context of 511 and batch size of 1
|
||||
// NOTE: since this functionality is mostly for debugging and demonstration purposes, we hardcode these
|
||||
// parameters here to keep things simple
|
||||
// IMPORTANT: do not use for anything else other than debugging and testing!
|
||||
LLAMA_API int llama_eval_export(struct llama_context * ctx, const char * fname);
|
||||
|
||||
// Convert the provided text into tokens.
|
||||
// The tokens pointer must be large enough to hold the resulting tokens.
|
||||
// Returns the number of tokens on success, no more than n_max_tokens
|
||||
|
|
|
|||
|
|
@ -12,6 +12,8 @@
|
|||
|
||||
const float MAX_QUANTIZATION_REFERENCE_ERROR = 0.0001;
|
||||
const float MAX_QUANTIZATION_TOTAL_ERROR = 0.002;
|
||||
const float MAX_QUANTIZATION_TOTAL_ERROR_2BITS = 0.0075;
|
||||
const float MAX_QUANTIZATION_TOTAL_ERROR_3BITS = 0.0040;
|
||||
const float MAX_DOT_PRODUCT_ERROR = 0.02;
|
||||
|
||||
const char* RESULT_STR[] = {"ok", "FAILED"};
|
||||
|
|
@ -122,7 +124,10 @@ int main(int argc, char * argv[]) {
|
|||
|
||||
if (qfns.quantize_row_q && qfns.dequantize_row_q) {
|
||||
const float total_error = total_quantization_error(qfns, test_size, test_data.data());
|
||||
failed = !(total_error < MAX_QUANTIZATION_TOTAL_ERROR);
|
||||
const float max_quantization_error =
|
||||
type == GGML_TYPE_Q2_K ? MAX_QUANTIZATION_TOTAL_ERROR_2BITS :
|
||||
type == GGML_TYPE_Q3_K ? MAX_QUANTIZATION_TOTAL_ERROR_3BITS : MAX_QUANTIZATION_TOTAL_ERROR;
|
||||
failed = !(total_error < max_quantization_error);
|
||||
num_failed += failed;
|
||||
if (failed || verbose) {
|
||||
printf("%5s absolute quantization error: %s (%f)\n", ggml_type_name(type), RESULT_STR[failed], total_error);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue