Skip to content

Commit 3cc5ed3

Browse files
make: fix nvcc optimization flags for host code (#5309)
1 parent 60ecf09 commit 3cc5ed3

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

Makefile

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -109,6 +109,7 @@ MK_NVCCFLAGS += -O3
109109
else
110110
MK_CFLAGS += -O3
111111
MK_CXXFLAGS += -O3
112+
MK_NVCCFLAGS += -O3
112113
endif
113114

114115
# clock_gettime came in POSIX.1b (1993)
@@ -365,7 +366,7 @@ ifdef LLAMA_CUBLAS
365366
MK_CPPFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include -I/usr/local/cuda/targets/aarch64-linux/include
366367
MK_LDFLAGS += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib -L/usr/local/cuda/targets/aarch64-linux/lib -L/usr/lib/wsl/lib
367368
OBJS += ggml-cuda.o
368-
MK_NVCCFLAGS = -use_fast_math
369+
MK_NVCCFLAGS += -use_fast_math
369370
ifndef JETSON_EOL_MODULE_DETECT
370371
MK_NVCCFLAGS += --forward-unknown-to-host-compiler
371372
endif # JETSON_EOL_MODULE_DETECT

0 commit comments

Comments
 (0)