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

Add Q4_3 support to cuBLAS (#1086)

Browse source
This commit is contained in:
slaren 2023-04-20 20:49:53 +02:00 • committed by GitHub
parent 8a1756abdf
commit 2005469ea1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 41 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Makefile
View file

@ -102,7 +102,7 @@ ifdef LLAMA_OPENBLAS
endif
ifdef LLAMA_CUBLAS
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include
LDFLAGS += -lcublas_static -lculibos -lcudart_static -lcublasLt_static -lpthread -ldl -lrt -L/usr/local/cuda/lib64
LDFLAGS += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64
OBJS += ggml-cuda.o
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
nvcc -arch=native -c -o $@ $<