CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

make: fix nvcc optimization flags for host code (#5309)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-02-03 20:14:59 +01:00
committed by GitHub
parent 60ecf099ed
commit 3cc5ed353c
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
Makefile
View File

@@ -109,6 +109,7 @@ MK_NVCCFLAGS += -O3
else else
MK_CFLAGS += -O3 MK_CFLAGS += -O3
MK_CXXFLAGS += -O3 MK_CXXFLAGS += -O3
MK_NVCCFLAGS += -O3
endif endif
# clock_gettime came in POSIX.1b (1993) # clock_gettime came in POSIX.1b (1993)
@@ -365,7 +366,7 @@ ifdef LLAMA_CUBLAS
MK_CPPFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include MK_CPPFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include
MK_LDFLAGS += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib MK_LDFLAGS += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
OBJS += ggml-cuda.o OBJS += ggml-cuda.o
MK_NVCCFLAGS = -use_fast_math MK_NVCCFLAGS += -use_fast_math
ifndef JETSON_EOL_MODULE_DETECT ifndef JETSON_EOL_MODULE_DETECT
MK_NVCCFLAGS += --forward-unknown-to-host-compiler MK_NVCCFLAGS += --forward-unknown-to-host-compiler
endif # JETSON_EOL_MODULE_DETECT endif # JETSON_EOL_MODULE_DETECT