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

Merge branch 'concedo' into concedo_experimental

Browse source
This commit is contained in:
Concedo 2023-06-15 14:47:32 +08:00
commit 6a113eeec8
1 changed files with 13 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Makefile
View file

@ -136,7 +136,7 @@ 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
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
OBJS += ggml-cuda.o ggml_v2-cuda.o
NVCC = nvcc
NVCCFLAGS = --forward-unknown-to-host-compiler -arch=native
ifdef LLAMA_CUDA_DMMV_X
@ -150,7 +150,9 @@ else
NVCCFLAGS += -DGGML_CUDA_DMMV_Y=1
endif # LLAMA_CUDA_DMMV_Y
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) $(CUBLAS_CXXFLAGS) -Wno-pedantic -c $< -o $@
ggml_v2-cuda.o: otherarch/ggml_v2-cuda.cu otherarch/ggml_v2-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) $(CUBLAS_CXXFLAGS) -Wno-pedantic -c $< -o $@
endif # LLAMA_CUBLAS
ifdef LLAMA_METAL