Docker build seems to be broken #4
Description
In a windows 10 machine, just did 'docker compose up --build' failed building with the error:
29.36 /BitNet/src/ggml-bitnet-mad.cpp:811:18: error: cannot initialize a variable of type 'int8_t *' (aka 'signed char *') with an rvalue of type 'const int8_t *' (aka 'const signed char *')
29.36 811 | int8_t * y_col = y + col * by;
29.36 | ^ ~~~~~~~~~~~~
here are full the logs:
[+] Building 372.2s (27/30)
=> [internal] load local bake definitions 0.0s
=> => reading from stdin 1.04kB 0.0s
=> [llm internal] load build definition from Dockerfile 0.1s
=> => transferring dockerfile: 1.66kB 0.0s
=> [web internal] load build definition from Dockerfile 0.1s
=> => transferring dockerfile: 332B 0.0s
=> [llm internal] load metadata for docker.io/library/python:3.9-alpine 1.4s
=> [web internal] load metadata for docker.io/library/node:16-alpine 0.7s
=> [web internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [web 1/5] FROM docker.io/library/node:16-alpine@sha256:a1f9d027912b58a7c75be7716c97cfbc6d3099f3a97ed84aa490be9dee20e787 0.0s
=> [web internal] load build context 0.0s
=> => transferring context: 8.75kB 0.0s
=> CACHED [web 2/5] WORKDIR /usr/src/app 0.0s
=> CACHED [web 3/5] COPY package*.json ./ 0.0s
=> CACHED [web 4/5] RUN npm install 0.0s
=> CACHED [web 5/5] COPY . . 0.0s
=> [web] exporting to image 0.0s
=> => exporting layers 0.0s
=> => writing image sha256:198647550290e92b02356da15ac2aaa46c753c7d92420b481986d0297422627f 0.0s
=> => naming to docker.io/library/bitnetjs-web 0.0s
=> [web] resolving provenance for metadata file 0.0s
=> [llm internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [llm 1/13] FROM docker.io/library/python:3.9-alpine@sha256:c99b6eb43b3ac4d750db3d6e8b22268d5ea9a99deead7218ce3deda7f2ca029c 7.2s
=> => resolve docker.io/library/python:3.9-alpine@sha256:c99b6eb43b3ac4d750db3d6e8b22268d5ea9a99deead7218ce3deda7f2ca029c 0.0s
=> => sha256:c99b6eb43b3ac4d750db3d6e8b22268d5ea9a99deead7218ce3deda7f2ca029c 10.29kB / 10.29kB 0.0s
=> => sha256:a381ce006821bdce2a0d62e601890f912e9f23d9e1fb61007e58328863bd7708 1.73kB / 1.73kB 0.0s
=> => sha256:ac5fec9ec2244c78ecbb822308adf80f8429fc6aa1ef08f75572ffdb2124470d 5.18kB / 5.18kB 0.0s
=> => sha256:2d35ebdb57d9971fea0cac1582aa78935adf8058b2cc32db163c98822e5dfa1b 3.80MB / 3.80MB 1.9s
=> => sha256:c9008197b8dd9d9b4c7a87e38fa66c8bceb4f7d87df8e9061284b123459f9451 456.92kB / 456.92kB 0.7s
=> => sha256:27711589a568cd76752066b7f5d51377b4eb3d501cf866ff9a2933d7c3db806d 15.40MB / 15.40MB 4.5s
=> => sha256:9806928fa0da94a3d2440c42430d7caa253e6f05e8669881cee924ceecabe3b3 247B / 247B 1.9s
=> => extracting sha256:2d35ebdb57d9971fea0cac1582aa78935adf8058b2cc32db163c98822e5dfa1b 0.3s
=> => extracting sha256:c9008197b8dd9d9b4c7a87e38fa66c8bceb4f7d87df8e9061284b123459f9451 0.3s
=> => extracting sha256:27711589a568cd76752066b7f5d51377b4eb3d501cf866ff9a2933d7c3db806d 2.4s
=> => extracting sha256:9806928fa0da94a3d2440c42430d7caa253e6f05e8669881cee924ceecabe3b3 0.0s
=> [llm internal] load build context 0.0s
=> => transferring context: 2.17kB 0.0s
=> [llm 11/13] ADD https://huggingface.co/brunopio/Llama3-8B-1.58-100B-tokens-GGUF/resolve/main/Llama3-8B-1.58-100B-tokens-TQ2_0.gguf . 262.0s
=> [llm 2/13] RUN apk add --no-cache build-base cmake clang git && rm -rf /var/cache/apk/* 22.7s
=> [llm 3/13] RUN git clone --recursive --depth 1 https://github.com/microsoft/BitNet.git && rm -rf BitNet/.git 28.4s
=> [llm 4/13] WORKDIR /BitNet 0.1s
=> [llm 5/13] RUN pip install --no-cache-dir -r requirements.txt 272.4s
=> [llm 6/13] COPY requirements-local.txt . 0.0s
=> [llm 7/13] RUN pip install --no-cache-dir -r requirements-local.txt 6.7s
=> [llm 8/13] RUN python3 utils/codegen_tl2.py --model Llama3-8B-1.58-100B-tokens --BM 256,128,256,128 --BK 96,96,96,96 --bm 32,32,32,32 0.4s
=> [llm 9/13] RUN cmake -B build -DBITNET_X86_TL2=ON -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ 2.6s
=> ERROR [llm 10/13] RUN cmake --build build --config Release 29.4s
------
> [llm 10/13] RUN cmake --build build --config Release:
0.311 [ 1%] Building C object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml.c.o
1.191 In file included from /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:7:
1.191 /BitNet/3rdparty/llama.cpp/ggml/src/ggml-quants.h:156:7: warning: no newline at end of file [-Wnewline-eof]
1.191 156 | #endif
1.191 | ^
1.245 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:1177:37: warning: cast from 'void (*)(const uint8_t *, float *, int64_t, const float)' (aka 'void (*)(const unsigned char *, float *, long, const float)') to 'ggml_to_float_t' (aka 'void (*)(const void *restrict, float *restrict, long)') converts to incompatible function type [-Wcast-function-type-mismatch]
1.245 1177 | .to_float = (ggml_to_float_t) dequantize_row_i2_s,
1.245 | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1.248 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:1184:37: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
1.248 1184 | .nrows = 1,
1.248 | ^
1.248 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:1181:37: note: previous initialization is here
1.248 1181 | .nrows = 1,
1.249 | ^
1.635 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12543:6: warning: no previous prototype for function 'float_act_quant' [-Wmissing-prototypes]
1.635 12543 | void float_act_quant(const int K, float* B, int32_t* dst, float* act_scale) {
1.635 | ^
1.635 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12543:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
1.635 12543 | void float_act_quant(const int K, float* B, int32_t* dst, float* act_scale) {
1.635 | ^
1.635 | static
1.637 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12563:18: warning: implicit conversion increases floating-point precision: 'float' to 'double' [-Wdouble-promotion]
1.637 12563 | if (fabs(A[i]) > max){
1.637 | ~~~~ ^~~~
1.638 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12564:32: warning: implicit conversion increases floating-point precision: 'float' to 'double' [-Wdouble-promotion]
1.638 12564 | i2_scale[0] = fabs(A[i]);
1.638 | ~~~~ ^~~~
1.638 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12574:37: warning: implicit conversion increases floating-point precision: 'float' to 'double' [-Wdouble-promotion]
1.638 12574 | dst[i] = (double)A[i] * i2_scale[0] > 0 ? 1 : -1;
1.638 | ~ ^~~~~~~~~~~
1.639 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12559:6: warning: no previous prototype for function 'weight_quant_f32' [-Wmissing-prototypes]
1.639 12559 | void weight_quant_f32(const int M, const int K, float* A, int32_t* dst, float* i2_scale) {
1.639 | ^
1.639 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12559:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
1.639 12559 | void weight_quant_f32(const int M, const int K, float* A, int32_t* dst, float* i2_scale) {
1.639 | ^
1.639 | static
1.643 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12583:18: warning: implicit conversion increases floating-point precision: 'float' to 'double' [-Wdouble-promotion]
1.643 12583 | if (fabs(temp_A) > max){
1.643 | ~~~~ ^~~~~~
1.643 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12584:32: warning: implicit conversion increases floating-point precision: 'float' to 'double' [-Wdouble-promotion]
1.643 12584 | i2_scale[0] = fabs(temp_A);
1.643 | ~~~~ ^~~~~~
1.645 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12595:39: warning: implicit conversion increases floating-point precision: 'float' to 'double' [-Wdouble-promotion]
1.645 12595 | dst[i] = (double)temp_A * i2_scale[0] > 0 ? 1 : -1;
1.645 | ~ ^~~~~~~~~~~
1.647 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12579:6: warning: no previous prototype for function 'weight_quant_f16' [-Wmissing-prototypes]
1.647 12579 | void weight_quant_f16(const int M, const int K, uint16_t* A, int32_t* dst, float* i2_scale) {
1.648 | ^
1.650 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12579:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
1.650 12579 | void weight_quant_f16(const int M, const int K, uint16_t* A, int32_t* dst, float* i2_scale) {
1.650 | ^
1.650 | static
1.652 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12600:6: warning: no previous prototype for function 'matrixMultiply_int' [-Wmissing-prototypes]
1.652 12600 | void matrixMultiply_int(const int M, const int N, const int K, const int32_t* A, const int32_t* B, int32_t* C) {
1.652 | ^
1.653 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12600:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
1.653 12600 | void matrixMultiply_int(const int M, const int N, const int K, const int32_t* A, const int32_t* B, int32_t* C) {
1.653 | ^
1.653 | static
1.659 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12765:29: warning: incompatible pointer types initializing 'bitnet_float_type *' (aka 'float *') with an expression of type 'char *' [-Wincompatible-pointer-types]
1.659 12765 | bitnet_float_type * bitnet_f_ptr = wdata;
1.659 | ^ ~~~~~
1.659 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12769:18: warning: initializing 'int8_t *' (aka 'signed char *') with an expression of type 'char *' converts between pointers to integer types where one is of the unique plain 'char' type and the other is not [-Wpointer-sign]
1.659 12769 | int8_t * three_qlut = cur_wdata;
1.659 | ^ ~~~~~~~~~
1.660 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12786:42: warning: passing 'const struct ggml_tensor *' to parameter of type 'struct ggml_tensor *' discards qualifiers [-Wincompatible-pointer-types-discards-qualifiers]
1.660 12786 | ggml_bitnet_transform_tensor(src0);
1.660 | ^~~~
1.660 /BitNet/3rdparty/llama.cpp/ggml/src/../../../../include/ggml-bitnet.h:35:65: note: passing argument to parameter 'tensor' here
1.660 35 | GGML_API void ggml_bitnet_transform_tensor(struct ggml_tensor * tensor);
1.660 | ^
1.661 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:12790:51: warning: incompatible pointer types passing 'bitnet_float_type *' (aka 'float *') to parameter of type 'ggml_fp16_t *' (aka 'unsigned short *') [-Wincompatible-pointer-types]
1.661 12790 | ggml_fp32_to_fp16_row(src1->data, bitnet_f_ptr, ne10 * ne11);
1.661 | ^~~~~~~~~~~~
1.661 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:541:59: note: passing argument to parameter 'y' here
1.661 541 | void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n) {
1.661 | ^
1.710 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:14084:26: warning: unused variable 'type' [-Wunused-variable]
1.710 14084 | const enum ggml_type type = src0->type;
1.710 | ^~~~
1.721 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:14291:48: warning: passing 'const struct ggml_compute_params *' to parameter of type 'struct ggml_compute_params *' discards qualifiers [-Wincompatible-pointer-types-discards-qualifiers]
1.721 14291 | ggml_compute_forward_get_rows_i2_s(params, dst);
1.721 | ^~~~~~
1.721 /BitNet/3rdparty/llama.cpp/ggml/src/ggml.c:14073:42: note: passing argument to parameter 'params' here
1.721 14073 | struct ggml_compute_params * params,
1.721 | ^
16.02 19 warnings generated.
16.05 [ 1%] Building C object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml-alloc.c.o
16.67 [ 2%] Building CXX object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml-backend.cpp.o
18.67 [ 3%] Building C object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/ggml-quants.c.o
18.76 In file included from /BitNet/3rdparty/llama.cpp/ggml/src/ggml-quants.c:4:
18.76 /BitNet/3rdparty/llama.cpp/ggml/src/ggml-quants.h:156:7: warning: no newline at end of file [-Wnewline-eof]
18.76 156 | #endif
18.76 | ^
20.23 /BitNet/3rdparty/llama.cpp/ggml/src/ggml-quants.c:16179:2: warning: no newline at end of file [-Wnewline-eof]
20.23 16179 | }
20.23 | ^
27.67 2 warnings generated.
27.70 [ 4%] Building CXX object 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/__/__/__/__/src/ggml-bitnet-mad.cpp.o
28.06 In file included from /BitNet/src/ggml-bitnet-mad.cpp:5:
28.06 In file included from /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-quants.h:4:
28.06 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:154:9: warning: anonymous structs are a GNU extension [-Wgnu-anonymous-struct]
28.06 154 | struct {
28.06 | ^
28.06 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:154:9: warning: anonymous types declared in an anonymous union are an extension [-Wnested-anon-types]
28.06 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:175:9: warning: anonymous structs are a GNU extension [-Wgnu-anonymous-struct]
28.06 175 | struct {
28.06 | ^
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:175:9: warning: anonymous types declared in an anonymous union are an extension [-Wnested-anon-types]
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:196:9: warning: anonymous structs are a GNU extension [-Wgnu-anonymous-struct]
28.07 196 | struct {
28.07 | ^
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:196:9: warning: anonymous types declared in an anonymous union are an extension [-Wnested-anon-types]
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:261:9: warning: anonymous structs are a GNU extension [-Wgnu-anonymous-struct]
28.07 261 | struct {
28.07 | ^
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:261:9: warning: anonymous types declared in an anonymous union are an extension [-Wnested-anon-types]
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:294:9: warning: anonymous structs are a GNU extension [-Wgnu-anonymous-struct]
28.07 294 | struct {
28.07 | ^
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:294:9: warning: anonymous types declared in an anonymous union are an extension [-Wnested-anon-types]
28.07 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:311:9: warning: anonymous structs are a GNU extension [-Wgnu-anonymous-struct]
28.07 311 | struct {
28.07 | ^
28.08 /BitNet/3rdparty/llama.cpp/ggml/src/./ggml-common.h:311:9: warning: anonymous types declared in an anonymous union are an extension [-Wnested-anon-types]
29.26 /BitNet/src/ggml-bitnet-mad.cpp:51:100: warning: unused parameter 'quant_weights' [-Wunused-parameter]
29.26 51 | size_t quantize_i2_s(const float * src, void * dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) {
29.26 | ^
29.26 /BitNet/src/ggml-bitnet-mad.cpp:200:39: warning: cast from 'const void *' to 'unsigned char *' drops const qualifier [-Wcast-qual]
29.26 200 | const uint8_t * x = (uint8_t *)vx;
29.26 | ^
29.26 /BitNet/src/ggml-bitnet-mad.cpp:201:38: warning: cast from 'const void *' to 'signed char *' drops const qualifier [-Wcast-qual]
29.26 201 | const int8_t * y = (int8_t *)vy;
29.26 | ^
29.27 /BitNet/src/ggml-bitnet-mad.cpp:198:56: warning: unused parameter 'bs' [-Wunused-parameter]
29.27 198 | void ggml_vec_dot_i2_i8_s_1x1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.27 | ^
29.27 /BitNet/src/ggml-bitnet-mad.cpp:198:112: warning: unused parameter 'by' [-Wunused-parameter]
29.27 198 | void ggml_vec_dot_i2_i8_s_1x1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.27 | ^
29.27 /BitNet/src/ggml-bitnet-mad.cpp:198:6: warning: no previous prototype for function 'ggml_vec_dot_i2_i8_s_1x1' [-Wmissing-prototypes]
29.27 198 | void ggml_vec_dot_i2_i8_s_1x1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.27 | ^
29.27 /BitNet/src/ggml-bitnet-mad.cpp:198:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
29.27 198 | void ggml_vec_dot_i2_i8_s_1x1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.27 | ^
29.27 | static
29.30 /BitNet/src/ggml-bitnet-mad.cpp:416:39: warning: cast from 'const void *' to 'unsigned char *' drops const qualifier [-Wcast-qual]
29.30 416 | const uint8_t * x = (uint8_t *)vx;
29.30 | ^
29.30 /BitNet/src/ggml-bitnet-mad.cpp:417:38: warning: cast from 'const void *' to 'signed char *' drops const qualifier [-Wcast-qual]
29.30 417 | const int8_t * y = (int8_t *)vy;
29.30 | ^
29.30 /BitNet/src/ggml-bitnet-mad.cpp:414:60: warning: unused parameter 'bs' [-Wunused-parameter]
29.30 414 | void ggml_vec_dot_i2_i8_s_1x4_32W(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.30 | ^
29.30 /BitNet/src/ggml-bitnet-mad.cpp:414:116: warning: unused parameter 'by' [-Wunused-parameter]
29.30 414 | void ggml_vec_dot_i2_i8_s_1x4_32W(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.30 | ^
29.30 /BitNet/src/ggml-bitnet-mad.cpp:414:6: warning: no previous prototype for function 'ggml_vec_dot_i2_i8_s_1x4_32W' [-Wmissing-prototypes]
29.30 414 | void ggml_vec_dot_i2_i8_s_1x4_32W(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.30 | ^
29.30 /BitNet/src/ggml-bitnet-mad.cpp:414:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
29.30 414 | void ggml_vec_dot_i2_i8_s_1x4_32W(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.30 | ^
29.30 | static
29.32 /BitNet/src/ggml-bitnet-mad.cpp:514:39: warning: cast from 'const void *' to 'unsigned char *' drops const qualifier [-Wcast-qual]
29.32 514 | const uint8_t * x = (uint8_t *)vx;
29.32 | ^
29.32 /BitNet/src/ggml-bitnet-mad.cpp:515:38: warning: cast from 'const void *' to 'signed char *' drops const qualifier [-Wcast-qual]
29.32 515 | const int8_t * y = (int8_t *)vy;
29.32 | ^
29.33 /BitNet/src/ggml-bitnet-mad.cpp:512:56: warning: unused parameter 'bs' [-Wunused-parameter]
29.33 512 | void ggml_vec_dot_i2_i8_s_1xN(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.33 | ^
29.33 /BitNet/src/ggml-bitnet-mad.cpp:512:112: warning: unused parameter 'by' [-Wunused-parameter]
29.33 512 | void ggml_vec_dot_i2_i8_s_1xN(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.33 | ^
29.33 /BitNet/src/ggml-bitnet-mad.cpp:512:6: warning: no previous prototype for function 'ggml_vec_dot_i2_i8_s_1xN' [-Wmissing-prototypes]
29.33 512 | void ggml_vec_dot_i2_i8_s_1xN(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.33 | ^
29.33 /BitNet/src/ggml-bitnet-mad.cpp:512:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
29.33 512 | void ggml_vec_dot_i2_i8_s_1xN(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.33 | ^
29.33 | static
29.36 /BitNet/src/ggml-bitnet-mad.cpp:793:39: warning: cast from 'const void *' to 'unsigned char *' drops const qualifier [-Wcast-qual]
29.36 793 | const uint8_t * x = (uint8_t *)vx;
29.36 | ^
29.36 /BitNet/src/ggml-bitnet-mad.cpp:794:38: warning: cast from 'const void *' to 'signed char *' drops const qualifier [-Wcast-qual]
29.36 794 | const int8_t * y = (int8_t *)vy;
29.36 | ^
29.36 /BitNet/src/ggml-bitnet-mad.cpp:811:18: error: cannot initialize a variable of type 'int8_t *' (aka 'signed char *') with an rvalue of type 'const int8_t *' (aka 'const signed char *')
29.36 811 | int8_t * y_col = y + col * by;
29.36 | ^ ~~~~~~~~~~~~
29.36 /BitNet/src/ggml-bitnet-mad.cpp:791:84: warning: unused parameter 'bx' [-Wunused-parameter]
29.36 791 | void ggml_vec_dot_i2_i8_s_Nx1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.36 | ^
29.36 /BitNet/src/ggml-bitnet-mad.cpp:791:6: warning: no previous prototype for function 'ggml_vec_dot_i2_i8_s_Nx1' [-Wmissing-prototypes]
29.36 791 | void ggml_vec_dot_i2_i8_s_Nx1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.36 | ^
29.36 /BitNet/src/ggml-bitnet-mad.cpp:791:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
29.36 791 | void ggml_vec_dot_i2_i8_s_Nx1(int n, float * s, size_t bs, const void * vx, size_t bx, const void * vy, size_t by, int nrc) {
29.36 | ^
29.36 | static
29.37 32 warnings and 1 error generated.
29.38 gmake[2]: *** [3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/build.make:135: 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/__/__/__/__/src/ggml-bitnet-mad.cpp.o] Error 1
29.38 gmake[1]: *** [CMakeFiles/Makefile2:978: 3rdparty/llama.cpp/ggml/src/CMakeFiles/ggml.dir/all] Error 2
29.38 gmake: *** [Makefile:136: all] Error 2
------
Dockerfile:28
--------------------
26 | RUN cmake -B build -DBITNET_X86_TL2=ON -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++
27 |
28 | >>> RUN cmake --build build --config Release
29 |
30 | # Download the Llama model from HuggingFace
--------------------
target llm: failed to solve: process "/bin/sh -c cmake --build build --config Release" did not complete successfully: exit code: 2