2024-02-09T04:55:24,171 Created temporary directory: /tmp/pip-build-tracker-2z74a8mh 2024-02-09T04:55:24,173 Initialized build tracking at /tmp/pip-build-tracker-2z74a8mh 2024-02-09T04:55:24,173 Created build tracker: /tmp/pip-build-tracker-2z74a8mh 2024-02-09T04:55:24,173 Entered build tracker: /tmp/pip-build-tracker-2z74a8mh 2024-02-09T04:55:24,174 Created temporary directory: /tmp/pip-wheel-v5s38yq8 2024-02-09T04:55:24,179 Created temporary directory: /tmp/pip-ephem-wheel-cache-zmsryim2 2024-02-09T04:55:24,208 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-09T04:55:24,212 2 location(s) to search for versions of llama-core: 2024-02-09T04:55:24,212 * https://pypi.org/simple/llama-core/ 2024-02-09T04:55:24,212 * https://www.piwheels.org/simple/llama-core/ 2024-02-09T04:55:24,213 Fetching project page and analyzing links: https://pypi.org/simple/llama-core/ 2024-02-09T04:55:24,213 Getting page https://pypi.org/simple/llama-core/ 2024-02-09T04:55:24,215 Found index url https://pypi.org/simple/ 2024-02-09T04:55:24,265 Fetched page https://pypi.org/simple/llama-core/ as application/vnd.pypi.simple.v1+json 2024-02-09T04:55:24,268 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/0c/3f/cd0eb8df269d2fef873ffcc04fe040ac5db0fea04d4f2cb4faf7cbfafac1/llama_core-0.0.1-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,269 Found link https://files.pythonhosted.org/packages/54/18/cfcca142a70d8179270564bb0d3ecdea14e025ee22af9ae7c36940515572/llama_core-0.0.1.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.1 2024-02-09T04:55:24,269 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/ec/7b/0b48decfb9fbc2076f5015faa1c62e75118c4ade6eb578d14c42eaa09c70/llama_core-0.0.2-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,269 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/89/25/f230d101e143cb48af28f86d5a3a60e5e6b37c7f93e3c646ca0151eda959/llama_core-0.0.2-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,270 Found link https://files.pythonhosted.org/packages/13/e0/942cd90aa6099469476699a34730f93ae98eec75637bcaaae05f30b671e5/llama_core-0.0.2.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.2 2024-02-09T04:55:24,270 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/16/8f/8bdffd743f5b585d172348cb0b4898599d502dcc4ca9776d1d59ddf04b0f/llama_core-0.0.3-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,270 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/5b/40/9058f432251845d67ea827068977a063ab628a9f20770c6d993705bef6ab/llama_core-0.0.3-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,271 Found link https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.3 2024-02-09T04:55:24,271 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-core/ 2024-02-09T04:55:24,272 Getting page https://www.piwheels.org/simple/llama-core/ 2024-02-09T04:55:24,273 Found index url https://www.piwheels.org/simple/ 2024-02-09T04:55:24,337 Fetched page https://www.piwheels.org/simple/llama-core/ as text/html 2024-02-09T04:55:24,340 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.3-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=60e4da9a7c59f727c521b26a7e2959af9d5e84a96fe28d9c5e31f658b74bc683 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,340 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.2-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=39b6da3d8b2c0a1bf4fe8ea9c6e0c25dc5ee291ba2d893e01751a684696ada6f (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,340 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.2-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=80df05f3984df31d62d543508bcf72719f7819fc924f4fe4aa2b8a14a3151fb5 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,341 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.1-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=0457a9c9fad48014762fe5e8eaacf08e7a030a8fa375ced00308fc00a32294d5 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,341 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.1-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=77646f382b23fba3fee5b1c6ca2af87609b49328e9c70e637104fb842bd80805 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T04:55:24,341 Skipping link: not a file: https://www.piwheels.org/simple/llama-core/ 2024-02-09T04:55:24,341 Skipping link: not a file: https://pypi.org/simple/llama-core/ 2024-02-09T04:55:24,359 Given no hashes to check 1 links for project 'llama-core': discarding no candidates 2024-02-09T04:55:24,375 Collecting llama-core==0.0.3 2024-02-09T04:55:24,378 Created temporary directory: /tmp/pip-unpack-63upco9p 2024-02-09T04:55:24,420 Downloading llama_core-0.0.3.tar.gz (10.6 MB) 2024-02-09T04:55:26,649 Added llama-core==0.0.3 from https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz to build tracker '/tmp/pip-build-tracker-2z74a8mh' 2024-02-09T04:55:26,654 Created temporary directory: /tmp/pip-build-env-zejhjp3c 2024-02-09T04:55:26,664 Installing build dependencies: started 2024-02-09T04:55:26,665 Running command pip subprocess to install build dependencies 2024-02-09T04:55:27,869 Using pip 23.3.1 from /home/piwheels/.local/lib/python3.9/site-packages/pip (python 3.9) 2024-02-09T04:55:28,392 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-09T04:55:28,740 Collecting scikit-build-core[pyproject] 2024-02-09T04:55:28,764 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.0-py3-none-any.whl (139 kB) 2024-02-09T04:55:29,054 Collecting exceptiongroup (from scikit-build-core[pyproject]) 2024-02-09T04:55:29,077 Using cached https://www.piwheels.org/simple/exceptiongroup/exceptiongroup-1.2.0-py3-none-any.whl (16 kB) 2024-02-09T04:55:29,246 Collecting packaging>=20.9 (from scikit-build-core[pyproject]) 2024-02-09T04:55:29,273 Using cached https://www.piwheels.org/simple/packaging/packaging-23.2-py3-none-any.whl (53 kB) 2024-02-09T04:55:29,388 Collecting tomli>=1.1 (from scikit-build-core[pyproject]) 2024-02-09T04:55:29,405 Using cached https://www.piwheels.org/simple/tomli/tomli-2.0.1-py3-none-any.whl (12 kB) 2024-02-09T04:55:29,541 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]) 2024-02-09T04:55:29,574 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-02-09T04:55:29,736 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]) 2024-02-09T04:55:29,755 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-02-09T04:55:31,453 Installing collected packages: tomli, pathspec, packaging, exceptiongroup, scikit-build-core, pyproject-metadata 2024-02-09T04:55:36,629 Successfully installed exceptiongroup-1.2.0 packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.0 tomli-2.0.1 2024-02-09T04:55:37,990 [notice] A new release of pip is available: 23.3.1 -> 24.0 2024-02-09T04:55:37,990 [notice] To update, run: python3 -m pip install --upgrade pip 2024-02-09T04:55:39,002 Installing build dependencies: finished with status 'done' 2024-02-09T04:55:39,009 Getting requirements to build wheel: started 2024-02-09T04:55:39,010 Running command Getting requirements to build wheel 2024-02-09T04:55:40,023 Getting requirements to build wheel: finished with status 'done' 2024-02-09T04:55:40,050 Installing backend dependencies: started 2024-02-09T04:55:40,051 Running command pip subprocess to install backend dependencies 2024-02-09T04:55:41,356 Using pip 23.3.1 from /home/piwheels/.local/lib/python3.9/site-packages/pip (python 3.9) 2024-02-09T04:55:41,944 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-09T04:55:42,750 Collecting cmake>=3.21 2024-02-09T04:55:42,785 Using cached https://www.piwheels.org/simple/cmake/cmake-3.28.1-cp39-cp39-linux_armv7l.whl (19.6 MB) 2024-02-09T04:55:47,453 Installing collected packages: cmake 2024-02-09T04:55:55,718 Creating /tmp/pip-build-env-zejhjp3c/normal/bin 2024-02-09T04:55:55,720 changing mode of /tmp/pip-build-env-zejhjp3c/normal/bin/cmake to 755 2024-02-09T04:55:55,723 changing mode of /tmp/pip-build-env-zejhjp3c/normal/bin/cpack to 755 2024-02-09T04:55:55,725 changing mode of /tmp/pip-build-env-zejhjp3c/normal/bin/ctest to 755 2024-02-09T04:55:55,804 Successfully installed cmake-3.28.1 2024-02-09T04:55:55,989 [notice] A new release of pip is available: 23.3.1 -> 24.0 2024-02-09T04:55:55,989 [notice] To update, run: python3 -m pip install --upgrade pip 2024-02-09T04:55:56,267 Installing backend dependencies: finished with status 'done' 2024-02-09T04:55:56,270 Created temporary directory: /tmp/pip-modern-metadata-r2tlerdy 2024-02-09T04:55:56,272 Preparing metadata (pyproject.toml): started 2024-02-09T04:55:56,273 Running command Preparing metadata (pyproject.toml) 2024-02-09T04:55:56,782 *** scikit-build-core 0.8.0 using CMake 3.28.1 (metadata_wheel) 2024-02-09T04:55:56,872 Preparing metadata (pyproject.toml): finished with status 'done' 2024-02-09T04:55:56,878 Source in /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2 has version 0.0.3, which satisfies requirement llama-core==0.0.3 from https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz 2024-02-09T04:55:56,879 Removed llama-core==0.0.3 from https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz from build tracker '/tmp/pip-build-tracker-2z74a8mh' 2024-02-09T04:55:56,886 Created temporary directory: /tmp/pip-unpack-6zwhxtq4 2024-02-09T04:55:56,887 Created temporary directory: /tmp/pip-unpack-datzjfnm 2024-02-09T04:55:56,894 Building wheels for collected packages: llama-core 2024-02-09T04:55:56,898 Created temporary directory: /tmp/pip-wheel-945enyj8 2024-02-09T04:55:56,899 Destination directory: /tmp/pip-wheel-945enyj8 2024-02-09T04:55:56,901 Building wheel for llama-core (pyproject.toml): started 2024-02-09T04:55:56,902 Running command Building wheel for llama-core (pyproject.toml) 2024-02-09T04:55:57,393 *** scikit-build-core 0.8.0 using CMake 3.28.1 (wheel) 2024-02-09T04:55:57,418 *** Configuring CMake... 2024-02-09T04:55:57,485 loading initial cache file /tmp/tmp9yw_3en6/build/CMakeInit.txt 2024-02-09T04:55:57,750 -- The C compiler identification is GNU 10.2.1 2024-02-09T04:55:58,069 -- The CXX compiler identification is GNU 10.2.1 2024-02-09T04:55:58,428 -- Detecting C compiler ABI info 2024-02-09T04:55:58,731 -- Detecting C compiler ABI info - done 2024-02-09T04:55:58,769 -- Check for working C compiler: /usr/bin/cc - skipped 2024-02-09T04:55:58,771 -- Detecting C compile features 2024-02-09T04:55:58,773 -- Detecting C compile features - done 2024-02-09T04:55:58,819 -- Detecting CXX compiler ABI info 2024-02-09T04:55:59,140 -- Detecting CXX compiler ABI info - done 2024-02-09T04:55:59,179 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-02-09T04:55:59,181 -- Detecting CXX compile features 2024-02-09T04:55:59,183 -- Detecting CXX compile features - done 2024-02-09T04:55:59,213 -- Found Git: /usr/bin/git (found version "2.30.2") 2024-02-09T04:55:59,272 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-02-09T04:55:59,613 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Failed 2024-02-09T04:55:59,614 -- Check if compiler accepts -pthread 2024-02-09T04:55:59,889 -- Check if compiler accepts -pthread - yes 2024-02-09T04:55:59,893 -- Found Threads: TRUE 2024-02-09T04:55:59,902 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-02-09T04:55:59,993 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-02-09T04:55:59,994 -- ARM detected 2024-02-09T04:55:59,997 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-02-09T04:56:00,314 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-02-09T04:56:00,349 CMake Warning (dev) at CMakeLists.txt:17 (install): 2024-02-09T04:56:00,350 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-09T04:56:00,350 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-09T04:56:00,350 CMake Warning (dev) at CMakeLists.txt:25 (install): 2024-02-09T04:56:00,350 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-09T04:56:00,351 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-09T04:56:00,359 -- Configuring done (2.9s) 2024-02-09T04:56:00,440 -- Generating done (0.1s) 2024-02-09T04:56:00,457 -- Build files have been written to: /tmp/tmp9yw_3en6/build 2024-02-09T04:56:00,468 *** Building project with Ninja... 2024-02-09T04:56:00,485 Change Dir: '/tmp/tmp9yw_3en6/build' 2024-02-09T04:56:00,485 Run Build Command(s): /usr/bin/ninja -v 2024-02-09T04:56:00,699 [1/22] cd /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp && /tmp/pip-build-env-zejhjp3c/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -DMSVC= -DCMAKE_C_COMPILER_VERSION=10.2.1 -DCMAKE_C_COMPILER_ID=GNU -DCMAKE_VS_PLATFORM_NAME= -DCMAKE_C_COMPILER=/usr/bin/cc -P /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-02-09T04:56:00,699 -- Found Git: /usr/bin/git (found version "2.30.2") 2024-02-09T04:56:00,914 [2/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/build-info.cpp 2024-02-09T04:56:02,766 [3/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/ggml-alloc.c 2024-02-09T04:56:07,140 [4/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/ggml-backend.c 2024-02-09T04:56:10,748 [5/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/console.cpp 2024-02-09T04:56:11,758 [6/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/sampling.cpp 2024-02-09T04:56:18,104 [7/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/grammar-parser.cpp 2024-02-09T04:56:23,241 [8/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wno-cast-qual -pthread -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/llava.cpp 2024-02-09T04:56:27,670 [9/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/train.cpp 2024-02-09T04:56:31,421 [10/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/ggml-quants.c 2024-02-09T04:56:35,683 [11/22] /usr/bin/c++ -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/../../common -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/llava-cli.cpp 2024-02-09T04:56:45,728 [12/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.cpp 2024-02-09T04:56:45,728 In file included from /usr/include/c++/10/vector:72, 2024-02-09T04:56:45,729 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-09T04:56:45,729 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/sampling.h:5, 2024-02-09T04:56:45,729 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.h:7, 2024-02-09T04:56:45,730 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.cpp:1: 2024-02-09T04:56:45,730 /usr/include/c++/10/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(std::vector<_Tp, _Alloc>::iterator, _Args&& ...) [with _Args = {const llama_model_kv_override&}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-02-09T04:56:45,731 /usr/include/c++/10/bits/vector.tcc:426:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-09T04:56:45,731 426 | vector<_Tp, _Alloc>:: 2024-02-09T04:56:45,731 | ^~~~~~~~~~~~~~~~~~~ 2024-02-09T04:56:45,732 /usr/include/c++/10/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(std::vector<_Tp, _Alloc>::iterator, _Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-02-09T04:56:45,732 /usr/include/c++/10/bits/vector.tcc:426:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-09T04:56:45,732 In file included from /usr/include/c++/10/vector:67, 2024-02-09T04:56:45,733 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-09T04:56:45,733 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/sampling.h:5, 2024-02-09T04:56:45,734 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.h:7, 2024-02-09T04:56:45,734 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.cpp:1: 2024-02-09T04:56:45,734 /usr/include/c++/10/bits/stl_vector.h: In function ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’: 2024-02-09T04:56:45,735 /usr/include/c++/10/bits/stl_vector.h:1198:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-09T04:56:45,735 1198 | _M_realloc_insert(end(), __x); 2024-02-09T04:56:45,735 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-09T04:56:45,736 In file included from /usr/include/c++/10/vector:72, 2024-02-09T04:56:45,736 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-09T04:56:45,736 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/sampling.h:5, 2024-02-09T04:56:45,737 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.h:7, 2024-02-09T04:56:45,737 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/common/common.cpp:1: 2024-02-09T04:56:45,737 /usr/include/c++/10/bits/vector.tcc:121:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-09T04:56:45,737 121 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-02-09T04:56:45,738 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T04:56:48,937 [13/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/ggml.c 2024-02-09T04:56:49,036 [14/22] : && /tmp/pip-build-env-zejhjp3c/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/libggml_static.a && /usr/bin/ar qc vendor/llama.cpp/libggml_static.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && : 2024-02-09T04:56:49,150 [15/22] : && /usr/bin/cc -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libggml_shared.so -o vendor/llama.cpp/libggml_shared.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -pthread && : 2024-02-09T04:57:05,732 [16/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wno-cast-qual -pthread -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/examples/llava/clip.cpp 2024-02-09T04:57:05,839 [17/22] : && /tmp/pip-build-env-zejhjp3c/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/examples/llava/libllava_static.a && /usr/bin/ar qc vendor/llama.cpp/examples/llava/libllava_static.a vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o && /usr/bin/ranlib vendor/llama.cpp/examples/llava/libllava_static.a && : 2024-02-09T04:57:32,872 [18/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp 2024-02-09T04:57:32,872 In file included from /usr/include/c++/10/vector:67, 2024-02-09T04:57:32,873 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.h:908, 2024-02-09T04:57:32,873 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:2: 2024-02-09T04:57:32,873 /usr/include/c++/10/bits/stl_vector.h: In function ‘std::vector<_Tp, _Alloc>::vector(std::initializer_list<_Tp>, const allocator_type&) [with _Tp = long long int; _Alloc = std::allocator]’: 2024-02-09T04:57:32,873 /usr/include/c++/10/bits/stl_vector.h:625:7: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,873 625 | vector(initializer_list __l, 2024-02-09T04:57:32,873 | ^~~~~~ 2024-02-09T04:57:32,873 /usr/include/c++/10/bits/stl_vector.h: In function ‘std::vector<_Tp, _Alloc>::vector(std::initializer_list<_Tp>, const allocator_type&) [with _Tp = long long int; _Alloc = std::allocator]’: 2024-02-09T04:57:32,873 /usr/include/c++/10/bits/stl_vector.h:625:7: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,874 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp: In function ‘bool llm_load_tensors(llama_model_loader&, llama_model&, int, llama_split_mode, int, const float*, bool, llama_progress_callback, void*)’: 2024-02-09T04:57:32,874 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3528:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,874 3528 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,874 | ^ 2024-02-09T04:57:32,874 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3532:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,874 3532 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,874 | ^ 2024-02-09T04:57:32,874 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3533:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,874 3533 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,875 | ^ 2024-02-09T04:57:32,875 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3563:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,875 3563 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-09T04:57:32,875 | ^ 2024-02-09T04:57:32,875 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3564:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,875 3564 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-09T04:57:32,875 | ^ 2024-02-09T04:57:32,875 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3565:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,876 3565 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-09T04:57:32,876 | ^ 2024-02-09T04:57:32,876 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3581:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,876 3581 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,876 | ^ 2024-02-09T04:57:32,876 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3583:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,876 3583 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,876 | ^ 2024-02-09T04:57:32,876 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3584:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,877 3584 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,877 | ^ 2024-02-09T04:57:32,877 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3609:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,877 3609 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,877 | ^ 2024-02-09T04:57:32,877 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3613:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,877 3613 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,877 | ^ 2024-02-09T04:57:32,877 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3614:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,878 3614 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,878 | ^ 2024-02-09T04:57:32,878 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3616:133: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,878 3616 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,878 | ^ 2024-02-09T04:57:32,878 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3618:133: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,878 3618 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-02-09T04:57:32,878 | ^ 2024-02-09T04:57:32,879 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3633:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,879 3633 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-02-09T04:57:32,879 | ^ 2024-02-09T04:57:32,879 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3634:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,879 3634 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-02-09T04:57:32,879 | ^ 2024-02-09T04:57:32,879 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3646:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,879 3646 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,879 | ^ 2024-02-09T04:57:32,880 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3647:132: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,880 3647 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-09T04:57:32,880 | ^ 2024-02-09T04:57:32,880 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3651:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,880 3651 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,880 | ^ 2024-02-09T04:57:32,880 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3652:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,880 3652 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,880 | ^ 2024-02-09T04:57:32,881 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3653:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,881 3653 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,881 | ^ 2024-02-09T04:57:32,881 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3683:121: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,881 3683 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,881 | ^ 2024-02-09T04:57:32,881 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3686:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,882 3686 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,882 | ^ 2024-02-09T04:57:32,882 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3687:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,882 3687 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,882 | ^ 2024-02-09T04:57:32,882 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3688:138: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,882 3688 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,883 | ^ 2024-02-09T04:57:32,883 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3724:127: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,883 3724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,883 | ^ 2024-02-09T04:57:32,883 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3725:118: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,883 3725 | model.tok_norm = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,883 | ^ 2024-02-09T04:57:32,883 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3726:118: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,884 3726 | model.tok_norm_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,884 | ^ 2024-02-09T04:57:32,884 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3730:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,884 3730 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,884 | ^ 2024-02-09T04:57:32,884 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3731:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,885 3731 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,885 | ^ 2024-02-09T04:57:32,885 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3732:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,885 3732 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,885 | ^ 2024-02-09T04:57:32,885 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3762:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,885 3762 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,885 | ^ 2024-02-09T04:57:32,886 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3766:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,886 3766 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,886 | ^ 2024-02-09T04:57:32,886 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3767:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,886 3767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,886 | ^ 2024-02-09T04:57:32,886 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3791:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,887 3791 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,887 | ^ 2024-02-09T04:57:32,887 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3795:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,887 3795 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,887 | ^ 2024-02-09T04:57:32,887 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3796:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,887 3796 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,887 | ^ 2024-02-09T04:57:32,888 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3797:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,888 3797 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,888 | ^ 2024-02-09T04:57:32,888 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3829:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,888 3829 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,888 | ^ 2024-02-09T04:57:32,888 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3833:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,888 3833 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,888 | ^ 2024-02-09T04:57:32,889 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3834:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,889 3834 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,889 | ^ 2024-02-09T04:57:32,889 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3858:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,889 3858 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,889 | ^ 2024-02-09T04:57:32,889 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3862:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,889 3862 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,890 | ^ 2024-02-09T04:57:32,890 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3863:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,890 3863 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,890 | ^ 2024-02-09T04:57:32,890 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3893:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,890 3893 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,890 | ^ 2024-02-09T04:57:32,891 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3897:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,891 3897 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,891 | ^ 2024-02-09T04:57:32,891 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3898:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,891 3898 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,891 | ^ 2024-02-09T04:57:32,892 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3899:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,892 3899 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,892 | ^ 2024-02-09T04:57:32,892 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3900:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,892 3900 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-02-09T04:57:32,892 | ^ 2024-02-09T04:57:32,892 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3916:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,893 3916 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-09T04:57:32,893 | ^ 2024-02-09T04:57:32,893 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3917:112: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,893 3917 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-02-09T04:57:32,893 | ^ 2024-02-09T04:57:32,893 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3919:124: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,893 3919 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T04:57:32,893 | ^ 2024-02-09T04:57:32,894 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3920:116: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,894 3920 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-09T04:57:32,894 | ^ 2024-02-09T04:57:32,894 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3922:124: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,894 3922 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T04:57:32,894 | ^ 2024-02-09T04:57:32,894 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3923:116: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,895 3923 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-09T04:57:32,895 | ^ 2024-02-09T04:57:32,895 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3938:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,895 3938 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,895 | ^ 2024-02-09T04:57:32,895 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3942:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,895 3942 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,895 | ^ 2024-02-09T04:57:32,896 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3943:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,896 3943 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,896 | ^ 2024-02-09T04:57:32,896 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3966:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,896 3966 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,896 | ^ 2024-02-09T04:57:32,896 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3967:134: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,896 3967 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-09T04:57:32,897 | ^ 2024-02-09T04:57:32,897 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3971:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,897 3971 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,897 | ^ 2024-02-09T04:57:32,897 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3972:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,897 3972 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,897 | ^ 2024-02-09T04:57:32,897 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:3973:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,898 3973 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,898 | ^ 2024-02-09T04:57:32,898 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4003:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,898 4003 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,898 | ^ 2024-02-09T04:57:32,898 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4007:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,898 4007 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,899 | ^ 2024-02-09T04:57:32,899 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4008:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,899 4008 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,899 | ^ 2024-02-09T04:57:32,899 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4009:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,899 4009 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,899 | ^ 2024-02-09T04:57:32,899 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4039:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,900 4039 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,900 | ^ 2024-02-09T04:57:32,900 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4041:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,900 4041 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,900 | ^ 2024-02-09T04:57:32,900 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4042:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,900 4042 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T04:57:32,900 | ^ 2024-02-09T04:57:32,900 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4043:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,901 4043 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,901 | ^ 2024-02-09T04:57:32,901 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4069:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,901 4069 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,901 | ^ 2024-02-09T04:57:32,901 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4073:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,901 4073 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T04:57:32,902 | ^ 2024-02-09T04:57:32,902 /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:4074:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T04:57:32,902 4074 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T04:57:32,902 | ^ 2024-02-09T04:57:32,902 In file included from /usr/include/c++/10/vector:72, 2024-02-09T04:57:32,902 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.h:908, 2024-02-09T04:57:32,902 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:2: 2024-02-09T04:57:32,902 /usr/include/c++/10/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(std::vector<_Tp, _Alloc>::iterator, _Args&& ...) [with _Args = {const double&}; _Tp = double; _Alloc = std::allocator]’: 2024-02-09T04:57:32,903 /usr/include/c++/10/bits/vector.tcc:426:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-09T04:57:32,903 426 | vector<_Tp, _Alloc>:: 2024-02-09T04:57:32,903 | ^~~~~~~~~~~~~~~~~~~ 2024-02-09T04:57:32,903 In file included from /usr/include/c++/10/vector:67, 2024-02-09T04:57:32,903 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.h:908, 2024-02-09T04:57:32,903 from /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/vendor/llama.cpp/llama.cpp:2: 2024-02-09T04:57:32,903 /usr/include/c++/10/bits/stl_vector.h: In member function ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’: 2024-02-09T04:57:32,904 /usr/include/c++/10/bits/stl_vector.h:1198:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-09T04:57:32,904 1198 | _M_realloc_insert(end(), __x); 2024-02-09T04:57:32,904 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-09T04:57:32,904 /usr/include/c++/10/bits/stl_vector.h:1198:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-09T04:57:32,904 1198 | _M_realloc_insert(end(), __x); 2024-02-09T04:57:32,904 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-09T04:57:33,305 [19/22] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllama.so -o vendor/llama.cpp/libllama.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -pthread && : 2024-02-09T04:57:33,395 [20/22] : && /tmp/pip-build-env-zejhjp3c/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/common/libcommon.a && /usr/bin/ar qc vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o && /usr/bin/ranlib vendor/llama.cpp/common/libcommon.a && : 2024-02-09T04:57:33,690 [21/22] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllava.so -o vendor/llama.cpp/examples/llava/libllava.so vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -Wl,-rpath,/tmp/tmp9yw_3en6/build/vendor/llama.cpp: vendor/llama.cpp/libllama.so -pthread && : 2024-02-09T04:57:33,818 [22/22] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -o vendor/llama.cpp/examples/llava/llava-cli -Wl,-rpath,/tmp/tmp9yw_3en6/build/vendor/llama.cpp: vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.so -pthread && : 2024-02-09T04:57:33,821 *** Installing project into wheel... 2024-02-09T04:57:33,838 -- Install configuration: "Release" 2024-02-09T04:57:33,842 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/lib/libggml_shared.so 2024-02-09T04:57:33,877 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-02-09T04:57:33,880 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-02-09T04:57:33,883 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/include/ggml.h 2024-02-09T04:57:33,888 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/include/ggml-alloc.h 2024-02-09T04:57:33,890 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/include/ggml-backend.h 2024-02-09T04:57:33,893 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/lib/libllama.so 2024-02-09T04:57:33,958 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/include/llama.h 2024-02-09T04:57:33,963 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/bin/convert.py 2024-02-09T04:57:33,967 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/bin/convert-lora-to-ggml.py 2024-02-09T04:57:33,972 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/llama_core/libllama.so 2024-02-09T04:57:34,034 -- Installing: /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/llama_core/libllama.so 2024-02-09T04:57:34,083 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/lib/libllava.so 2024-02-09T04:57:34,109 -- Set non-toolchain portion of runtime path of "/tmp/tmp9yw_3en6/wheel/platlib/lib/libllava.so" to "" 2024-02-09T04:57:34,135 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/bin/llava-cli 2024-02-09T04:57:34,148 -- Set non-toolchain portion of runtime path of "/tmp/tmp9yw_3en6/wheel/platlib/bin/llava-cli" to "" 2024-02-09T04:57:34,168 -- Installing: /tmp/tmp9yw_3en6/wheel/platlib/llama_core/libllava.so 2024-02-09T04:57:34,186 -- Set non-toolchain portion of runtime path of "/tmp/tmp9yw_3en6/wheel/platlib/llama_core/libllava.so" to "" 2024-02-09T04:57:34,214 -- Installing: /tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/llama_core/libllava.so 2024-02-09T04:57:34,234 -- Set non-toolchain portion of runtime path of "/tmp/pip-wheel-v5s38yq8/llama-core_b23c95ce461040cc8924cc4c25d126e2/llama_core/libllava.so" to "" 2024-02-09T04:57:34,266 *** Making wheel... 2024-02-09T04:57:35,568 *** Created llama_core-0.0.3-cp39-cp39-manylinux_2_31_armv7l.whl... 2024-02-09T04:57:35,625 Building wheel for llama-core (pyproject.toml): finished with status 'done' 2024-02-09T04:57:35,653 Created wheel for llama-core: filename=llama_core-0.0.3-cp39-cp39-manylinux_2_31_armv7l.whl size=2269792 sha256=e4d3e1d0928d8e196bb3629af0ffc3c81c6cc27b7829b3d237e1754e54e00cc6 2024-02-09T04:57:35,654 Stored in directory: /tmp/pip-ephem-wheel-cache-zmsryim2/wheels/a3/ff/ba/46260e00971448f78d7730241483a4c8d9a0ebebb015359cbc 2024-02-09T04:57:35,667 Successfully built llama-core 2024-02-09T04:57:35,735 Removed build tracker: '/tmp/pip-build-tracker-2z74a8mh'