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

CUDA: fixed LLAMA_FAST compilation option (#2473)

Browse source
This commit is contained in:
Johannes Gäßler 2023-07-31 21:02:19 +02:00 committed by GitHub
parent b772bba42e
commit 49e7cb5bb1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
Makefile
View file

@ -243,7 +243,7 @@ ifdef LLAMA_CUDA_CCBIN
NVCCFLAGS += -ccbin $(LLAMA_CUDA_CCBIN)
endif
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
$(NVCC) $(NVCCFLAGS) $(subst -Ofast,-O3,$(CXXFLAGS)) -Wno-pedantic -c $< -o $@
endif # LLAMA_CUBLAS
ifdef LLAMA_CLBLAST