microsoft
On Android device, compilation fails.
I installed the Debian system on my Android phone using Termux, and then followed the instructions step by step until I ran “python3 setup_env.py -md models/Falcon3-7B-Instruct-1.58bit -q i2_s” the following error occurred.
[ 1%] Building C object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml.c.o cc1: warning: command-line option ‘-fpermissive’ is valid for C++/ObjC++ but not for C /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12514:6: warning: no previous prototype for ‘float_act_quant’ [-Wmissing-prototypes] 12514 | void float_act_quant(const int K, float* B, int32_t* dst, float* act_scale) { | ^~~~~~~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12530:6: warning: no previous prototype for ‘weight_quant_f32’ [-Wmissing-prototypes] 12530 | void weight_quant_f32(const int M, const int K, float* A, int32_t* dst, float* i2_scale) { | ^~~~~~~~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c: In function ‘weight_quant_f32’: /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12545:35: warning: implicit conversion from ‘float’ to ‘double’ to match other operand of binary expression [-Wdouble-promotion] 12545 | dst[i] = (double)A[i] * i2_scale[0] > 0 ? 1 : -1; | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c: At top level: /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12550:6: warning: no previous prototype for ‘weight_quant_f16’ [-Wmissing-prototypes] 12550 | void weight_quant_f16(const int M, const int K, uint16_t* A, int32_t* dst, float* i2_scale) { | ^~~~~~~~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c: In function ‘weight_quant_f16’: /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12566:37: warning: implicit conversion from ‘float’ to ‘double’ to match other operand of binary expression [-Wdouble-promotion] 12566 | dst[i] = (double)temp_A * i2_scale[0] > 0 ? 1 : -1; | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c: At top level: /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12571:6: warning: no previous prototype for ‘matrixMultiply_int’ [-Wmissing-prototypes] 12571 | void matrixMultiply_int(const int M, const int N, const int K, const int32_t* A, const int32_t* B, int32_t* C) { | ^~~~~~~~~~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c: In function ‘ggml_compute_forward_mul_mat’: /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12660:44: warning: initialization of ‘bitnet_float_type ’ {aka ‘float ’} from incompatible pointer type ‘char ’ [-Wincompatible-pointer-types] 12660 | bitnet_float_type * bitnet_f_ptr = wdata; | ^~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12664:25: warning: pointer targets in initialization of ‘int8_t ’ {aka ‘signed char ’} from ‘char ’ differ in signedness [-Wpointer-sign] 12664 | int8_t * qlut = cur_wdata; | ^~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12675:42: warning: passing argument 1 of ‘ggml_bitnet_transform_tensor’ discards ‘const’ qualifier from pointer target type [-Wdiscarded-qualifiers] 12675 | ggml_bitnet_transform_tensor(src0); | ^~~~ In file included from /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:50: /root/BitNet/3rdparty/llama.cpp/ggml/src/../../../../include/ggml-bitnet.h:35:65: note: expected ‘struct ggml_tensor ’ but argument is of type ‘const struct ggml_tensor ’ 35 | GGML_API void ggml_bitnet_transform_tensor(struct ggml_tensor * tensor); | ~~~~~~~~~~~~~~~~~~~~~^~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12679:51: warning: passing argument 2 of ‘ggml_fp32_to_fp16_row’ from incompatible pointer type [-Wincompatible-pointer-types] 12679 | ggml_fp32_to_fp16_row(src1->data, bitnet_f_ptr, ne10 * ne11); | ^~~~~~~~~~~~ | | | bitnet_float_type * {aka float } /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:541:59: note: expected ‘ggml_fp16_t ’ {aka ‘short unsigned int ’} but argument is of type ‘bitnet_float_type ’ {aka ‘float ’} 541 | void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n) { | ~~~~~~~~~~~~~~^ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12722:50: warning: passing argument 1 of ‘ggml_fp16_to_fp32_row’ from incompatible pointer type [-Wincompatible-pointer-types] 12722 | ggml_fp16_to_fp32_row(act_output + dst_offset, (float ) dst->data + dst_offset, ne01 / n_tile_num); | ~~~~~~~~~~~^~~~~~~~~~~~ | | | bitnet_float_type * {aka float } /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:535:48: note: expected ‘const ggml_fp16_t ’ {aka ‘const short unsigned int ’} but argument is of type ‘bitnet_float_type ’ {aka ‘float ’} 535 | void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int64_t n) { | ~~~~~~~~~~~~~~~~~~~~^ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12712:23: warning: unused variable ‘qlut_offset’ [-Wunused-variable] 12712 | const int qlut_offset = 0; | ^~~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12702:19: warning: unused variable ‘lut_tile_size’ [-Wunused-variable] 12702 | const int lut_tile_size = lut_size / n_tile_num; | ^~~~~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12666:29: warning: unused variable ‘lut_biases’ [-Wunused-variable] 12666 | bitnet_float_type * lut_biases = (bitnet_float_type ) (lut_scales + wt->lut_scales_size * ne11); | ^~~~~~~~~~ /root/BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12653:19: warning: unused variable ‘bits’ [-Wunused-variable] 12653 | const int bits = ggml_bitnet_get_type_bits(type); | ^~~~ [ 2%] Building C object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml-alloc.c.o cc1: warning: command-line option ‘-fpermissive’ is valid for C++/ObjC++ but not for C [ 3%] Building CXX object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml-backend.cpp.o [ 4%] Building C object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml-quants.c.o cc1: warning: command-line option ‘-fpermissive’ is valid for C++/ObjC++ but not for C [ 5%] Building CXX object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/////src/ggml-bitnet-mad.cpp.o In file included from /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-quants.h:4, from /root/BitNet/src/ggml-bitnet-mad.cpp:5: /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:154:16: warning: ISO C++ prohibits anonymous structs [-Wpedantic] 154 | struct { | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:175:16: warning: ISO C++ prohibits anonymous structs [-Wpedantic] 175 | struct { | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:196:16: warning: ISO C++ prohibits anonymous structs [-Wpedantic] 196 | struct { | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:261:16: warning: ISO C++ prohibits anonymous structs [-Wpedantic] 261 | struct { | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:294:16: warning: ISO C++ prohibits anonymous structs [-Wpedantic] 294 | struct { | ^ /root/BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:311:16: warning: ISO C++ prohibits anonymous structs [-Wpedantic] 311 | struct { | ^ /root/BitNet/src/ggml-bitnet-mad.cpp: In function ‘size_t quantize_i2_s(const float, void, int64_t, int64_t, const float)’: /root/BitNet/src/ggml-bitnet-mad.cpp:46:100: warning: unused parameter ‘quant_weights’ [-Wunused-parameter] 46 | size_t quantize_i2_s(const float * src, void * dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) { | ~~~~~~~~~~~~~~^~~~~~~~~~~~~ /root/BitNet/src/ggml-bitnet-mad.cpp: In function ‘void ggml_vec_dot_i2_i8_s(int, float, size_t, const void, size_t, const void, size_t, int)’: /root/BitNet/src/ggml-bitnet-mad.cpp:95:28: warning: cast from type ‘const void’ to type ‘uint8_t’ {aka ‘unsigned char’} casts away qualifiers [-Wcast-qual] 95 | const uint8_t * x = (uint8_t )vx; | ^~~~~~~~~~~~~ /root/BitNet/src/ggml-bitnet-mad.cpp:96:28: warning: cast from type ‘const void’ to type ‘int8_t’ {aka ‘signed char’} casts away qualifiers [-Wcast-qual] 96 | const int8_t * y = (int8_t )vy; | ^~~~~~~~~~~~ /root/BitNet/src/ggml-bitnet-mad.cpp:94:52: warning: unused parameter ‘bs’ [-Wunused-parameter] 94 | void ggml_vec_dot_i2_i8_s(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) { | ~~~~~~~^~ /root/BitNet/src/ggml-bitnet-mad.cpp:94:80: warning: unused parameter ‘bx’ [-Wunused-parameter] 94 | void ggml_vec_dot_i2_i8_s(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) { | ~~~~~~~^~ /root/BitNet/src/ggml-bitnet-mad.cpp:94:108: warning: unused parameter ‘by’ [-Wunused-parameter] 94 | void ggml_vec_dot_i2_i8_s(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) { | ~~~~~~~^~ /root/BitNet/src/ggml-bitnet-mad.cpp:94:116: warning: unused parameter ‘nrc’ [-Wunused-parameter] 94 | void ggml_vec_dot_i2_i8_s(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) { | ~~~~^~~ during GIMPLE pass: vect /root/BitNet/src/ggml-bitnet-mad.cpp: In function ‘size_t quantize_i2_s(const float, void, int64_t, int64_t, const float)’: /root/BitNet/src/ggml-bitnet-mad.cpp:46:8: internal compiler error: in vect_transform_reduction, at tree-vect-loop.cc:7457 46 | size_t quantize_i2_s(const float * src, void * dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) { | ^~~~~~~~~~~~~ 0x18e9327 internal_error(char const, ...) ???:0 0x6a6c8f fancy_abort(char const, int, char const) ???:0 0xf6c43b vect_transform_reduction(_loop_vec_info, _stmt_vec_info, gimple_stmt_iterator, gimple*, _slp_tree*) ???:0 0x18aedcf vect_transform_stmt(vec_info*, _stmt_vec_info*, gimple_stmt_iterator*, _slp_tree*, _slp_instance*) ???:0 0xf79bcf vect_transform_loop(_loop_vec_info*, gimple*) ???:0 Please submit a full bug report, with preprocessed source (by using -freport-bug). Please include the complete backtrace with any bug report. See file:///usr/share/doc/gcc-12/README.Bugs for instructions. gmake[2]: *** [3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/build.make:132: 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/////src/ggml-bitnet-mad.cpp.o] Error 1 gmake[1]: *** [CMakeFiles/Makefile2:759: 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/all] Error 2 gmake: *** [Makefile:136: all] Error 2
Can anyone help me?
It seems like you're using gcc instead of clang, try specifying clang. I solved it using this command:
cmake -DBITNET_ARM_TL1=ON -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -B build
