mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 05:48:47 +01:00
7296c961d9
* Allow use of OpenCL GPU-based BLAS using ClBlast instead of OpenBLAS for context processing * Improve ClBlast implementation, avoid recreating buffers, remove redundant transfers * Finish merge of ClBlast support * Move CLBlast implementation to separate file Add buffer reuse code (adapted from slaren's cuda implementation) * Add q4_2 and q4_3 CLBlast support, improve code * Double CLBlast speed by disabling OpenBLAS thread workaround Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com> Co-authored-by: slaren <2141330+slaren@users.noreply.github.com> * Fix device selection env variable names * Fix cast in opencl kernels * Add CLBlast to CMakeLists.txt * Replace buffer pool with static buffers a, b, qb, c Fix compile warnings * Fix typos, use GGML_TYPE defines, improve code * Improve btype dequant kernel selection code, add error if type is unsupported * Improve code quality * Move internal stuff out of header * Use internal enums instead of CLBlast enums * Remove leftover C++ includes and defines * Make event use easier to read Co-authored-by: Henri Vasserman <henv@hot.ee> * Use c compiler for opencl files * Simplify code, fix include * First check error, then release event * Make globals static, fix indentation * Rename dequant kernels file to conform with other file names * Fix import cl file name --------- Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com> Co-authored-by: slaren <2141330+slaren@users.noreply.github.com> Co-authored-by: Henri Vasserman <henv@hot.ee> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
214 lines
5.9 KiB
Makefile
214 lines
5.9 KiB
Makefile
# Define the default target now so that it is always the first target
|
|
default: main quantize quantize-stats perplexity embedding vdot
|
|
|
|
ifndef UNAME_S
|
|
UNAME_S := $(shell uname -s)
|
|
endif
|
|
|
|
ifndef UNAME_P
|
|
UNAME_P := $(shell uname -p)
|
|
endif
|
|
|
|
ifndef UNAME_M
|
|
UNAME_M := $(shell uname -m)
|
|
endif
|
|
|
|
CCV := $(shell $(CC) --version | head -n 1)
|
|
CXXV := $(shell $(CXX) --version | head -n 1)
|
|
|
|
# Mac OS + Arm can report x86_64
|
|
# ref: https://github.com/ggerganov/whisper.cpp/issues/66#issuecomment-1282546789
|
|
ifeq ($(UNAME_S),Darwin)
|
|
ifneq ($(UNAME_P),arm)
|
|
SYSCTL_M := $(shell sysctl -n hw.optional.arm64 2>/dev/null)
|
|
ifeq ($(SYSCTL_M),1)
|
|
# UNAME_P := arm
|
|
# UNAME_M := arm64
|
|
warn := $(warning Your arch is announced as x86_64, but it seems to actually be ARM64. Not fixing that can lead to bad performance. For more info see: https://github.com/ggerganov/whisper.cpp/issues/66\#issuecomment-1282546789)
|
|
endif
|
|
endif
|
|
endif
|
|
|
|
#
|
|
# Compile flags
|
|
#
|
|
|
|
# keep standard at C11 and C++11
|
|
CFLAGS = -I. -O3 -DNDEBUG -std=c11 -fPIC
|
|
CXXFLAGS = -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC
|
|
LDFLAGS =
|
|
|
|
# warnings
|
|
CFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith
|
|
CXXFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar
|
|
|
|
# OS specific
|
|
# TODO: support Windows
|
|
ifeq ($(UNAME_S),Linux)
|
|
CFLAGS += -pthread
|
|
CXXFLAGS += -pthread
|
|
endif
|
|
ifeq ($(UNAME_S),Darwin)
|
|
CFLAGS += -pthread
|
|
CXXFLAGS += -pthread
|
|
endif
|
|
ifeq ($(UNAME_S),FreeBSD)
|
|
CFLAGS += -pthread
|
|
CXXFLAGS += -pthread
|
|
endif
|
|
ifeq ($(UNAME_S),NetBSD)
|
|
CFLAGS += -pthread
|
|
CXXFLAGS += -pthread
|
|
endif
|
|
ifeq ($(UNAME_S),OpenBSD)
|
|
CFLAGS += -pthread
|
|
CXXFLAGS += -pthread
|
|
endif
|
|
ifeq ($(UNAME_S),Haiku)
|
|
CFLAGS += -pthread
|
|
CXXFLAGS += -pthread
|
|
endif
|
|
|
|
# Architecture specific
|
|
# TODO: probably these flags need to be tweaked on some architectures
|
|
# feel free to update the Makefile for your architecture and send a pull request or issue
|
|
ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686))
|
|
# Use all CPU extensions that are available:
|
|
CFLAGS += -march=native -mtune=native
|
|
CXXFLAGS += -march=native -mtune=native
|
|
|
|
# Usage AVX-only
|
|
#CFLAGS += -mfma -mf16c -mavx
|
|
#CXXFLAGS += -mfma -mf16c -mavx
|
|
endif
|
|
ifneq ($(filter ppc64%,$(UNAME_M)),)
|
|
POWER9_M := $(shell grep "POWER9" /proc/cpuinfo)
|
|
ifneq (,$(findstring POWER9,$(POWER9_M)))
|
|
CFLAGS += -mcpu=power9
|
|
CXXFLAGS += -mcpu=power9
|
|
endif
|
|
# Require c++23's std::byteswap for big-endian support.
|
|
ifeq ($(UNAME_M),ppc64)
|
|
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).
|
|
ifeq ($(UNAME_S),Darwin)
|
|
CFLAGS += -DGGML_USE_ACCELERATE
|
|
LDFLAGS += -framework Accelerate
|
|
endif
|
|
endif
|
|
ifdef LLAMA_OPENBLAS
|
|
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas
|
|
LDFLAGS += -lopenblas
|
|
endif
|
|
ifdef LLAMA_CUBLAS
|
|
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
|
|
LDFLAGS += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib
|
|
OBJS += ggml-cuda.o
|
|
NVCC = nvcc
|
|
NVCCFLAGS = --forward-unknown-to-host-compiler -arch=native
|
|
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
|
|
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
|
|
endif
|
|
ifdef LLAMA_CLBLAST
|
|
CFLAGS += -DGGML_USE_CLBLAST
|
|
LDFLAGS += -lclblast -lOpenCL
|
|
OBJS += ggml-opencl.o
|
|
ggml-opencl.o: ggml-opencl.c ggml-opencl.h
|
|
$(CC) $(CFLAGS) -c $< -o $@
|
|
endif
|
|
ifdef LLAMA_GPROF
|
|
CFLAGS += -pg
|
|
CXXFLAGS += -pg
|
|
endif
|
|
ifdef LLAMA_PERF
|
|
CFLAGS += -DGGML_PERF
|
|
CXXFLAGS += -DGGML_PERF
|
|
endif
|
|
ifneq ($(filter aarch64%,$(UNAME_M)),)
|
|
CFLAGS += -mcpu=native
|
|
CXXFLAGS += -mcpu=native
|
|
endif
|
|
ifneq ($(filter armv6%,$(UNAME_M)),)
|
|
# Raspberry Pi 1, 2, 3
|
|
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access
|
|
endif
|
|
ifneq ($(filter armv7%,$(UNAME_M)),)
|
|
# Raspberry Pi 4
|
|
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
|
|
endif
|
|
ifneq ($(filter armv8%,$(UNAME_M)),)
|
|
# Raspberry Pi 4
|
|
CFLAGS += -mfp16-format=ieee -mno-unaligned-access
|
|
endif
|
|
|
|
#
|
|
# Print build information
|
|
#
|
|
|
|
$(info I llama.cpp build info: )
|
|
$(info I UNAME_S: $(UNAME_S))
|
|
$(info I UNAME_P: $(UNAME_P))
|
|
$(info I UNAME_M: $(UNAME_M))
|
|
$(info I CFLAGS: $(CFLAGS))
|
|
$(info I CXXFLAGS: $(CXXFLAGS))
|
|
$(info I LDFLAGS: $(LDFLAGS))
|
|
$(info I CC: $(CCV))
|
|
$(info I CXX: $(CXXV))
|
|
$(info )
|
|
|
|
#
|
|
# Build library
|
|
#
|
|
|
|
ggml.o: ggml.c ggml.h
|
|
$(CC) $(CFLAGS) -c $< -o $@
|
|
|
|
llama.o: llama.cpp ggml.h llama.h llama_util.h
|
|
$(CXX) $(CXXFLAGS) -c $< -o $@
|
|
|
|
common.o: examples/common.cpp examples/common.h
|
|
$(CXX) $(CXXFLAGS) -c $< -o $@
|
|
|
|
clean:
|
|
rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-q4_0-matmult
|
|
|
|
main: examples/main/main.cpp ggml.o llama.o common.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
|
@echo
|
|
@echo '==== Run ./main -h for help. ===='
|
|
@echo
|
|
|
|
quantize: examples/quantize/quantize.cpp ggml.o llama.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
|
|
|
quantize-stats: examples/quantize-stats/quantize-stats.cpp ggml.o llama.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
|
|
|
perplexity: examples/perplexity/perplexity.cpp ggml.o llama.o common.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
|
|
|
embedding: examples/embedding/embedding.cpp ggml.o llama.o common.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
|
|
|
vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
|
|
|
libllama.so: llama.o ggml.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
|
|
|
|
#
|
|
# Tests
|
|
#
|
|
|
|
benchmark: examples/benchmark/benchmark-q4_0-matmult.c ggml.o $(OBJS)
|
|
$(CXX) $(CXXFLAGS) $^ -o benchmark-q4_0-matmult $(LDFLAGS)
|
|
./benchmark-q4_0-matmult
|
|
|
|
.PHONY: tests
|
|
tests:
|
|
bash ./tests/run-tests.sh
|