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

Merge branch 'master' into mpi

Browse source
This commit is contained in:
Evan Miller 2023-07-09 15:02:19 -04:00
commit 0f557c2ac4
22 changed files with 759 additions and 503 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Makefile
View file

@ -172,7 +172,12 @@ ifdef LLAMA_CUBLAS
LDFLAGS += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib
OBJS += ggml-cuda.o
NVCC = nvcc
NVCCFLAGS = --forward-unknown-to-host-compiler -arch=native
NVCCFLAGS = --forward-unknown-to-host-compiler
ifdef CUDA_DOCKER_ARCH
NVCCFLAGS += -Wno-deprecated-gpu-targets -arch=$(CUDA_DOCKER_ARCH)
else
NVCCFLAGS += -arch=native
endif # CUDA_DOCKER_ARCH
ifdef LLAMA_CUDA_FORCE_DMMV
NVCCFLAGS += -DGGML_CUDA_FORCE_DMMV
endif # LLAMA_CUDA_FORCE_DMMV
@ -196,6 +201,7 @@ ifdef LLAMA_CUDA_KQUANTS_ITER
else
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
endif
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
endif # LLAMA_CUBLAS