root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 21:39:52 +00:00
Code Issues Actions 12 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
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
Makefile
View File

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