Try to compile on Xavier

[fenixlam]

I don't know if koboldcpp can run on Nvidia Xavier. So I given a try. But it failed. I wonder if we can have chance to fix it.

> make LLAMA_OPENBLAS=1 LLAMA_CLBLAST=1

I llama.cpp build info: 
I UNAME_S:  Linux
I UNAME_P:  aarch64
I UNAME_M:  aarch64
I CFLAGS:   -I.              -I./include -I./include/CL -I./otherarch -I./otherarch/tools -Ofast -DNDEBUG -std=c11   -fPIC -DGGML_USE_K_QUANTS -pthread -s -pthread 
I CXXFLAGS: -I. -I./examples -I./include -I./include/CL -I./otherarch -I./otherarch/tools -O3 -DNDEBUG -std=c++11 -fPIC -pthread -s -Wno-multichar -Wno-write-strings -pthread 
I LDFLAGS:  
I CC:       cc (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) 7.5.0
I CXX:      g++ (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) 7.5.0

cc  -I.              -I./include -I./include/CL -I./otherarch -I./otherarch/tools -Ofast -DNDEBUG -std=c11   -fPIC -DGGML_USE_K_QUANTS -pthread -s -pthread   -c k_quants.c -o k_quants.o
k_quants.c: In function ‘ggml_vec_dot_q2_K_q8_K’:
k_quants.c:1037:36: warning: implicit declaration of function ‘vld1q_s16_x2’; did you mean ‘vld1q_s16’? [-Wimplicit-function-declaration]
         const int16x8x2_t q8sums = vld1q_s16_x2(y[i].bsums);
                                    ^~~~~~~~~~~~
                                    vld1q_s16
k_quants.c:1037:36: error: invalid initializer
k_quants.c:1074:41: warning: implicit declaration of function ‘vld1q_u8_x2’; did you mean ‘vld1q_u32’? [-Wimplicit-function-declaration]
             const uint8x16x2_t q2bits = vld1q_u8_x2(q2); q2 += 32;
                                         ^~~~~~~~~~~
                                         vld1q_u32
k_quants.c:1074:41: error: invalid initializer
k_quants.c:1076:35: warning: implicit declaration of function ‘vld1q_s8_x2’; did you mean ‘vld1q_s32’? [-Wimplicit-function-declaration]
             int8x16x2_t q8bytes = vld1q_s8_x2(q8); q8 += 32;
                                   ^~~~~~~~~~~
                                   vld1q_s32
k_quants.c:1076:35: error: invalid initializer
k_quants.c:1066:17: error: incompatible types when assigning to type ‘int8x16x2_t {aka struct int8x16x2_t}’ from type ‘int’
         q8bytes = vld1q_s8_x2(q8); q8 += 32;\
                 ^
k_quants.c:1081:13: note: in expansion of macro ‘SHIFT_MULTIPLY_ACCUM_WITH_SCALE’
             SHIFT_MULTIPLY_ACCUM_WITH_SCALE(2, 2);
             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
k_quants.c:1066:17: error: incompatible types when assigning to type ‘int8x16x2_t {aka struct int8x16x2_t}’ from type ‘int’
         q8bytes = vld1q_s8_x2(q8); q8 += 32;\
                 ^
k_quants.c:1083:13: note: in expansion of macro ‘SHIFT_MULTIPLY_ACCUM_WITH_SCALE’
             SHIFT_MULTIPLY_ACCUM_WITH_SCALE(4, 4);
             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
k_quants.c:1066:17: error: incompatible types when assigning to type ‘int8x16x2_t {aka struct int8x16x2_t}’ from type ‘int’
         q8bytes = vld1q_s8_x2(q8); q8 += 32;\
                 ^
k_quants.c:1085:13: note: in expansion of macro ‘SHIFT_MULTIPLY_ACCUM_WITH_SCALE’
             SHIFT_MULTIPLY_ACCUM_WITH_SCALE(6, 6);
             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
k_quants.c: In function ‘ggml_vec_dot_q3_K_q8_K’:
k_quants.c:1243:31: error: invalid initializer
         uint8x16x2_t qhbits = vld1q_u8_x2(qh);
                               ^~~~~~~~~~~
k_quants.c:1261:41: error: invalid initializer
             const uint8x16x2_t q3bits = vld1q_u8_x2(q3); q3 += 32;
                                         ^~~~~~~~~~~
k_quants.c:1262:43: warning: implicit declaration of function ‘vld1q_s8_x4’; did you mean ‘vld1q_s64’? [-Wimplicit-function-declaration]
             const int8x16x4_t q8bytes_1 = vld1q_s8_x4(q8); q8 += 64;
                                           ^~~~~~~~~~~
                                           vld1q_s64
k_quants.c:1262:43: error: invalid initializer
k_quants.c:1263:43: error: invalid initializer
             const int8x16x4_t q8bytes_2 = vld1q_s8_x4(q8); q8 += 64;
                                           ^~~~~~~~~~~
k_quants.c: In function ‘ggml_vec_dot_q4_K_q8_K’:
k_quants.c:1560:41: error: invalid initializer
             const uint8x16x2_t q4bits = vld1q_u8_x2(q4); q4 += 32;
                                         ^~~~~~~~~~~
k_quants.c:1578:21: error: incompatible types when assigning to type ‘int8x16x2_t {aka struct int8x16x2_t}’ from type ‘int’
             q8bytes = vld1q_s8_x2(q8); q8 += 32;
                     ^
k_quants.c:1587:21: error: incompatible types when assigning to type ‘int8x16x2_t {aka struct int8x16x2_t}’ from type ‘int’
             q8bytes = vld1q_s8_x2(q8); q8 += 32;
                     ^
k_quants.c: In function ‘ggml_vec_dot_q5_K_q8_K’:
k_quants.c:1782:31: error: invalid initializer
         uint8x16x2_t qhbits = vld1q_u8_x2(qh);
                               ^~~~~~~~~~~
k_quants.c:1790:41: error: invalid initializer
             const uint8x16x2_t q5bits = vld1q_u8_x2(q5); q5 += 32;
                                         ^~~~~~~~~~~
k_quants.c:1791:41: error: invalid initializer
             const int8x16x4_t q8bytes = vld1q_s8_x4(q8); q8 += 64;
                                         ^~~~~~~~~~~
k_quants.c: In function ‘ggml_vec_dot_q6_K_q8_K’:
k_quants.c:2008:36: error: invalid initializer
         const int16x8x2_t q8sums = vld1q_s16_x2(y[i].bsums);
                                    ^~~~~~~~~~~~
k_quants.c:2022:35: error: invalid initializer
             uint8x16x2_t qhbits = vld1q_u8_x2(qh); qh += 32;
                                   ^~~~~~~~~~~
k_quants.c:2023:35: warning: implicit declaration of function ‘vld1q_u8_x4’; did you mean ‘vld1q_u64’? [-Wimplicit-function-declaration]
             uint8x16x4_t q6bits = vld1q_u8_x4(q6); q6 += 64;
                                   ^~~~~~~~~~~
                                   vld1q_u64
k_quants.c:2023:35: error: invalid initializer
k_quants.c:2024:35: error: invalid initializer
             int8x16x4_t q8bytes = vld1q_s8_x4(q8); q8 += 64;
                                   ^~~~~~~~~~~
k_quants.c:2067:21: error: incompatible types when assigning to type ‘int8x16x4_t {aka struct int8x16x4_t}’ from type ‘int’
             q8bytes = vld1q_s8_x4(q8); q8 += 64;
                     ^
Makefile:259: recipe for target 'k_quants.o' failed
make: *** [k_quants.o] Error 1

[LostRuins]

You gcc and g++ seems a little old. Can you try update it?

[fenixlam]

I try to update the gcc and g++, but I failed. So I try another way. Clone the project on google colab, and try to make it, return no target?

[LostRuins]

Are you sure you are in the correct folder? There is a make file in the project root.