build : on Mac OS enable Metal by default (#2901)
* build : on Mac OS enable Metal by default * make : try to fix build on Linux * make : move targets back to the top * make : fix target clean * llama : enable GPU inference by default with Metal * llama : fix vocab_only logic when GPU is enabled * common : better `n_gpu_layers` assignment * readme : update Metal instructions * make : fix merge conflict remnants * gitignore : metal
This commit is contained in:
parent
bd33e5ab92
commit
e36ecdccc8
9 changed files with 143 additions and 133 deletions
76
Makefile
76
Makefile
|
@ -7,6 +7,39 @@ TEST_TARGETS = tests/test-llama-grammar tests/test-grammar-parser tests/test-dou
|
|||
# Code coverage output files
|
||||
COV_TARGETS = *.gcno tests/*.gcno *.gcda tests/*.gcda *.gcov tests/*.gcov lcov-report gcovr-report
|
||||
|
||||
ifndef UNAME_S
|
||||
UNAME_S := $(shell uname -s)
|
||||
endif
|
||||
|
||||
ifndef UNAME_P
|
||||
UNAME_P := $(shell uname -p)
|
||||
endif
|
||||
|
||||
ifndef UNAME_M
|
||||
UNAME_M := $(shell uname -m)
|
||||
endif
|
||||
|
||||
# Mac OS + Arm can report x86_64
|
||||
# ref: https://github.com/ggerganov/whisper.cpp/issues/66#issuecomment-1282546789
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
ifndef LLAMA_NO_METAL
|
||||
LLAMA_METAL := 1
|
||||
endif
|
||||
|
||||
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 := $(warning Your arch is announced as x86_64, but it seems to actually be ARM64. Not fixing that can lead to bad performance. For more info see: https://github.com/ggerganov/whisper.cpp/issues/66\#issuecomment-1282546789)
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifneq '' '$(or $(filter clean,$(MAKECMDGOALS)),$(LLAMA_METAL))'
|
||||
BUILD_TARGETS += metal
|
||||
endif
|
||||
|
||||
default: $(BUILD_TARGETS)
|
||||
|
||||
test:
|
||||
|
@ -38,18 +71,6 @@ gcovr-report: coverage ## Generate gcovr report
|
|||
mkdir -p gcovr-report
|
||||
gcovr --root . --html --html-details --output gcovr-report/coverage.html
|
||||
|
||||
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
|
||||
|
||||
ifdef RISCV_CROSS_COMPILE
|
||||
CC := riscv64-unknown-linux-gnu-gcc
|
||||
CXX := riscv64-unknown-linux-gnu-g++
|
||||
|
@ -58,19 +79,6 @@ 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 := $(warning Your arch is announced as x86_64, but it seems to actually be ARM64. Not fixing that can lead to bad performance. For more info see: https://github.com/ggerganov/whisper.cpp/issues/66\#issuecomment-1282546789)
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
#
|
||||
# Compile flags
|
||||
#
|
||||
|
@ -231,14 +239,24 @@ endif
|
|||
endif
|
||||
|
||||
ifndef LLAMA_NO_ACCELERATE
|
||||
# Mac M1 - include Accelerate framework.
|
||||
# `-framework Accelerate` works on Mac Intel as well, with negliable performance boost (as of the predict time).
|
||||
# Mac OS - include Accelerate framework.
|
||||
# `-framework Accelerate` works both with Apple Silicon and Mac Intel
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
MK_CPPFLAGS += -DGGML_USE_ACCELERATE
|
||||
MK_LDFLAGS += -framework Accelerate
|
||||
endif
|
||||
endif # LLAMA_NO_ACCELERATE
|
||||
|
||||
ifdef LLAMA_METAL
|
||||
# By default - use GPU acceleration on Mac OS
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
CFLAGS += -DGGML_USE_METAL #-DGGML_METAL_NDEBUG
|
||||
CXXFLAGS += -DGGML_USE_METAL
|
||||
LDFLAGS += -framework Foundation -framework Metal -framework MetalKit
|
||||
OBJS += ggml-metal.o
|
||||
endif
|
||||
endif # LLAMA_METAL
|
||||
|
||||
ifdef LLAMA_MPI
|
||||
MK_CPPFLAGS += -DGGML_USE_MPI
|
||||
MK_CFLAGS += -Wno-cast-qual
|
||||
|
@ -480,10 +498,6 @@ beam-search: examples/beam-search/beam-search.cpp build-info.h ggml.o llama.o co
|
|||
speculative: examples/speculative/speculative.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
ifneq '' '$(or $(filter clean,$(MAKECMDGOALS)),$(LLAMA_METAL))'
|
||||
BUILD_TARGETS += metal
|
||||
endif
|
||||
|
||||
ifdef LLAMA_METAL
|
||||
metal: examples/metal/metal.cpp ggml.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue