Error compiling under raspberry pi

[zevlg]

[pi@raspberrypi:...ub/alpaca.cpp]$ make chat
I llama.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  unknown
I UNAME_M:  armv7l
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:  
I CC:       cc (Raspbian 8.3.0-6+rpi1) 8.3.0
I CXX:      g++ (Raspbian 8.3.0-6+rpi1) 8.3.0

cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations   -c ggml.c -o ggml.o
ggml.c: In function ‘ggml_vec_mad_q4_0’:
ggml.c:1778:35: warning: implicit declaration of function ‘vzip1_s8’; did you mean ‘vzipq_s8’? [-Wimplicit-function-declaration]
             const int8x8_t vxlt = vzip1_s8(vxls, vxhs);
                                   ^~~~~~~~
                                   vzipq_s8
ggml.c:1778:35: error: incompatible types when initializing type ‘int8x8_t’ using type ‘int’
ggml.c:1779:35: warning: implicit declaration of function ‘vzip2_s8’; did you mean ‘vzipq_s8’? [-Wimplicit-function-declaration]
             const int8x8_t vxht = vzip2_s8(vxls, vxhs);
                                   ^~~~~~~~
                                   vzipq_s8
ggml.c:1779:35: error: incompatible types when initializing type ‘int8x8_t’ using type ‘int’
make: *** [Makefile:186: ggml.o] Error 1
[2][pi@raspberrypi:...ub/alpaca.cpp]$ 

[davidrimshnick]

Same....

[davidrimshnick]

Seems like lines 1778 and 1779 of ggml.c should be changed from

            const int8x8_t vxlt = vzip1_s8(vxls, vxhs);
            const int8x8_t vxht = vzip2_s8(vxls, vxhs);

to

            const int8x8_t vxlt = vget_low_s8(vcombine_s8(vxls, vxhs));
            const int8x8_t vxht = vget_high_s8(vcombine_s8(vxls, vxhs));

[108062138]

@davidrimshnick I follow your steps to compile the chat model from source code in raspberry pi 4 and successfully compile such model. But it turns out the model can't be loaded into raspberrypi. I wonder if u meet such problem before?

pi@raspberrypi:~/Desktop/alpaca.cpp $ make chat
I llama.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  unknown
I UNAME_M:  armv7l
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:  
I CC:       cc (Raspbian 10.2.1-6+rpi1) 10.2.1 20210110
I CXX:      g++ (Raspbian 10.2.1-6+rpi1) 10.2.1 20210110

make: 'chat' is up to date.
pi@raspberrypi:~/Desktop/alpaca.cpp $ ./chat
main: seed = 1680591939
llama_model_load: loading model from 'ggml-alpaca-7b-q4.bin' - please wait ...
llama_model_load: failed to open 'ggml-alpaca-7b-q4.bin'
main: failed to load model from 'ggml-alpaca-7b-q4.bin'
pi@raspberrypi:~/Desktop/alpaca.cpp $