Issue when make libllama.so with LLAMA_CUBLAS=1

[exppii]

I prepare to use text-generation-webui，and enable CUBLAS; so I try build libllama.so for myself. then I got this error:

[root@A12-213P llama.cpp]# LLAMA_CUBLAS=1 make libllama.so
I llama.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  x86_64
I UNAME_M:  x86_64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -pthread -march=native -mtune=native -DGGML_USE_CUBLAS -I/usr/local/cuda/include
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native
I LDFLAGS:  -lcublas_static -lculibos -lcudart_static -lcublasLt_static -lpthread -ldl -L/usr/local/cuda/lib64 -lrt
I CC:       cc (GCC) 11.2.1 20220127 (Red Hat 11.2.1-9)
I CXX:      g++ (GCC) 11.2.1 20220127 (Red Hat 11.2.1-9)

g++ -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -march=native -mtune=native -shared -fPIC -o libllama.so llama.o ggml.o ggml-cuda.o -lcublas_static -lculibos -lcudart_static -lcublasLt_static -lpthread -ldl -L/usr/local/cuda/lib64
/opt/rh/devtoolset-11/root/usr/libexec/gcc/x86_64-redhat-linux/11/ld: ggml-cuda.o: relocation R_X86_64_32 against `.bss' can not be used when making a shared object; recompile with -fPIC
collect2: error: ld returned 1 exit status
make: *** [Makefile:184：libllama.so] 错误 1
[root@A12-213P llama.cpp]# 

[slaren]

does it help if you add -fPIC to the nvcc line in the Makefile?
https://github.com/ggerganov/llama.cpp/blob/5addcb120cf2682c7ede0b1c520592700d74c87c/Makefile#L107-L108

[exppii]

THX,
After add --compiler-options -fPIC at line 108 in the Makefile resolves the problem.

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 -lrt
        OBJS    += ggml-cuda.o
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
        nvcc -arch=native --compiler-options -fPIC -c -o $@ $<

[slaren]

This will be fixed in #1094