ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add NVIDIA cuBLAS support (#1044)

Browse source
This commit is contained in:
slaren 2023-04-19 11:22:45 +02:00 • committed by GitHub
parent 6667401238
commit 8944a13296
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 221 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

4
Makefile
View file

@ -97,6 +97,10 @@ ifdef LLAMA_OPENBLAS
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas
LDFLAGS += -lopenblas
endif
ifdef LLAMA_CUBLAS
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include
LDFLAGS += -lcublas_static -lculibos -lcudart_static -lcublasLt_static -lpthread -ldl -L/usr/local/cuda/lib64
endif
ifdef LLAMA_GPROF
CFLAGS += -pg
CXXFLAGS += -pg