diff options
Diffstat (limited to 'Makefile')
| -rw-r--r-- | Makefile | 33 |
1 files changed, 27 insertions, 6 deletions
@@ -105,6 +105,7 @@ 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,$(POWER9_M))) @@ -116,6 +117,7 @@ ifneq ($(filter ppc64%,$(UNAME_M)),) CXXFLAGS += -std=c++23 -DGGML_BIG_ENDIAN endif endif + ifndef LLAMA_NO_ACCELERATE # Mac M1 - include Accelerate framework. # `-framework Accelerate` works on Mac Intel as well, with negliable performance boost (as of the predict time). @@ -123,7 +125,8 @@ ifndef LLAMA_NO_ACCELERATE CFLAGS += -DGGML_USE_ACCELERATE LDFLAGS += -framework Accelerate endif -endif +endif # LLAMA_NO_ACCELERATE + ifdef LLAMA_OPENBLAS CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas -I/usr/include/openblas ifneq ($(shell grep -e "Arch Linux" -e "ID_LIKE=arch" /etc/os-release 2>/dev/null),) @@ -131,11 +134,13 @@ 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 @@ -156,9 +161,10 @@ endif # LLAMA_CUDA_DMMV_Y ggml-cuda.o: ggml-cuda.cu ggml-cuda.h $(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@ endif # LLAMA_CUBLAS + ifdef LLAMA_CLBLAST - CFLAGS += -DGGML_USE_CLBLAST - CXXFLAGS += -DGGML_USE_CLBLAST + CFLAGS += -DGGML_USE_CLBLAST + CXXFLAGS += -DGGML_USE_CLBLAST # Mac provides OpenCL as a framework ifeq ($(UNAME_S),Darwin) LDFLAGS += -lclblast -framework OpenCL @@ -166,23 +172,38 @@ 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_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 |