2024-02-08T12:47:06,203 Created temporary directory: /tmp/pip-build-tracker-jndmbokv 2024-02-08T12:47:06,204 Initialized build tracking at /tmp/pip-build-tracker-jndmbokv 2024-02-08T12:47:06,205 Created build tracker: /tmp/pip-build-tracker-jndmbokv 2024-02-08T12:47:06,205 Entered build tracker: /tmp/pip-build-tracker-jndmbokv 2024-02-08T12:47:06,206 Created temporary directory: /tmp/pip-wheel-3oti5nny 2024-02-08T12:47:06,209 Created temporary directory: /tmp/pip-ephem-wheel-cache-byfd2sgw 2024-02-08T12:47:06,231 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-08T12:47:06,234 2 location(s) to search for versions of llama-core: 2024-02-08T12:47:06,234 * https://pypi.org/simple/llama-core/ 2024-02-08T12:47:06,234 * https://www.piwheels.org/simple/llama-core/ 2024-02-08T12:47:06,235 Fetching project page and analyzing links: https://pypi.org/simple/llama-core/ 2024-02-08T12:47:06,236 Getting page https://pypi.org/simple/llama-core/ 2024-02-08T12:47:06,237 Found index url https://pypi.org/simple/ 2024-02-08T12:47:06,457 Fetched page https://pypi.org/simple/llama-core/ as application/vnd.pypi.simple.v1+json 2024-02-08T12:47:06,459 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) 2024-02-08T12:47:06,460 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 2024-02-08T12:47:06,461 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) 2024-02-08T12:47:06,461 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) 2024-02-08T12:47:06,462 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 2024-02-08T12:47:06,463 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-core/ 2024-02-08T12:47:06,464 Getting page https://www.piwheels.org/simple/llama-core/ 2024-02-08T12:47:06,465 Found index url https://www.piwheels.org/simple/ 2024-02-08T12:47:06,619 Fetched page https://www.piwheels.org/simple/llama-core/ as text/html 2024-02-08T12:47:06,621 Skipping link: not a file: https://www.piwheels.org/simple/llama-core/ 2024-02-08T12:47:06,621 Skipping link: not a file: https://pypi.org/simple/llama-core/ 2024-02-08T12:47:06,641 Given no hashes to check 1 links for project 'llama-core': discarding no candidates 2024-02-08T12:47:06,660 Collecting llama-core==0.0.1 2024-02-08T12:47:06,663 Created temporary directory: /tmp/pip-unpack-qjoz8590 2024-02-08T12:47:06,887 Downloading llama_core-0.0.1.tar.gz (10.6 MB) 2024-02-08T12:47:13,734 Added llama-core==0.0.1 from https://files.pythonhosted.org/packages/54/18/cfcca142a70d8179270564bb0d3ecdea14e025ee22af9ae7c36940515572/llama_core-0.0.1.tar.gz to build tracker '/tmp/pip-build-tracker-jndmbokv' 2024-02-08T12:47:13,739 Created temporary directory: /tmp/pip-build-env-sc8k3i1k 2024-02-08T12:47:13,743 Installing build dependencies: started 2024-02-08T12:47:13,744 Running command pip subprocess to install build dependencies 2024-02-08T12:47:14,892 Using pip 23.3.1 from /home/piwheels/.local/lib/python3.11/site-packages/pip (python 3.11) 2024-02-08T12:47:15,430 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-08T12:47:15,864 Collecting scikit-build-core[pyproject] 2024-02-08T12:47:15,881 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.0-py3-none-any.whl (139 kB) 2024-02-08T12:47:16,170 Collecting packaging>=20.9 (from scikit-build-core[pyproject]) 2024-02-08T12:47:16,184 Using cached https://www.piwheels.org/simple/packaging/packaging-23.2-py3-none-any.whl (53 kB) 2024-02-08T12:47:16,287 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]) 2024-02-08T12:47:16,309 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-02-08T12:47:16,383 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]) 2024-02-08T12:47:16,397 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-02-08T12:47:20,210 Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata 2024-02-08T12:47:20,900 Successfully installed packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.0 2024-02-08T12:47:21,162 [notice] A new release of pip is available: 23.3.1 -> 24.0 2024-02-08T12:47:21,162 [notice] To update, run: python3 -m pip install --upgrade pip 2024-02-08T12:47:21,396 Installing build dependencies: finished with status 'done' 2024-02-08T12:47:21,400 Getting requirements to build wheel: started 2024-02-08T12:47:21,401 Running command Getting requirements to build wheel 2024-02-08T12:47:21,829 Getting requirements to build wheel: finished with status 'done' 2024-02-08T12:47:21,855 Created temporary directory: /tmp/pip-modern-metadata-mu47p94_ 2024-02-08T12:47:21,857 Preparing metadata (pyproject.toml): started 2024-02-08T12:47:21,858 Running command Preparing metadata (pyproject.toml) 2024-02-08T12:47:22,360 *** scikit-build-core 0.8.0 using CMake 3.25.1 (metadata_wheel) 2024-02-08T12:47:22,455 Preparing metadata (pyproject.toml): finished with status 'done' 2024-02-08T12:47:22,460 Source in /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a has version 0.0.1, which satisfies requirement llama-core==0.0.1 from https://files.pythonhosted.org/packages/54/18/cfcca142a70d8179270564bb0d3ecdea14e025ee22af9ae7c36940515572/llama_core-0.0.1.tar.gz 2024-02-08T12:47:22,461 Removed llama-core==0.0.1 from https://files.pythonhosted.org/packages/54/18/cfcca142a70d8179270564bb0d3ecdea14e025ee22af9ae7c36940515572/llama_core-0.0.1.tar.gz from build tracker '/tmp/pip-build-tracker-jndmbokv' 2024-02-08T12:47:22,466 Created temporary directory: /tmp/pip-unpack-kz2gxnt8 2024-02-08T12:47:22,467 Created temporary directory: /tmp/pip-unpack-y6ouixdd 2024-02-08T12:47:22,474 Building wheels for collected packages: llama-core 2024-02-08T12:47:22,481 Created temporary directory: /tmp/pip-wheel-jp5li54_ 2024-02-08T12:47:22,482 Destination directory: /tmp/pip-wheel-jp5li54_ 2024-02-08T12:47:22,484 Building wheel for llama-core (pyproject.toml): started 2024-02-08T12:47:22,485 Running command Building wheel for llama-core (pyproject.toml) 2024-02-08T12:47:22,976 *** scikit-build-core 0.8.0 using CMake 3.25.1 (wheel) 2024-02-08T12:47:22,996 *** Configuring CMake... 2024-02-08T12:47:23,134 loading initial cache file /tmp/tmp8b630dc1/build/CMakeInit.txt 2024-02-08T12:47:23,411 -- The C compiler identification is GNU 12.2.0 2024-02-08T12:47:23,714 -- The CXX compiler identification is GNU 12.2.0 2024-02-08T12:47:23,763 -- Detecting C compiler ABI info 2024-02-08T12:47:24,044 -- Detecting C compiler ABI info - done 2024-02-08T12:47:24,082 -- Check for working C compiler: /usr/bin/cc - skipped 2024-02-08T12:47:24,084 -- Detecting C compile features 2024-02-08T12:47:24,086 -- Detecting C compile features - done 2024-02-08T12:47:24,104 -- Detecting CXX compiler ABI info 2024-02-08T12:47:24,414 -- Detecting CXX compiler ABI info - done 2024-02-08T12:47:24,452 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-02-08T12:47:24,454 -- Detecting CXX compile features 2024-02-08T12:47:24,456 -- Detecting CXX compile features - done 2024-02-08T12:47:24,488 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-08T12:47:24,545 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-02-08T12:47:24,865 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-02-08T12:47:24,870 -- Found Threads: TRUE 2024-02-08T12:47:24,878 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-02-08T12:47:24,979 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-02-08T12:47:24,980 -- ARM detected 2024-02-08T12:47:24,983 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-02-08T12:47:25,286 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-02-08T12:47:25,327 CMake Warning (dev) at CMakeLists.txt:19 (install): 2024-02-08T12:47:25,327 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-08T12:47:25,328 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-08T12:47:25,329 CMake Warning (dev) at CMakeLists.txt:28 (install): 2024-02-08T12:47:25,329 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-08T12:47:25,330 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-08T12:47:25,336 -- Configuring done 2024-02-08T12:47:25,406 -- Generating done 2024-02-08T12:47:25,424 -- Build files have been written to: /tmp/tmp8b630dc1/build 2024-02-08T12:47:25,436 *** Building project with Ninja... 2024-02-08T12:47:25,788 [1/22] cd /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp && /usr/bin/cmake -DMSVC= -DCMAKE_C_COMPILER_VERSION=12.2.0 -DCMAKE_C_COMPILER_ID=GNU -DCMAKE_VS_PLATFORM_NAME= -DCMAKE_C_COMPILER=/usr/bin/cc -P /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-02-08T12:47:25,788 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-08T12:47:25,995 [2/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/build-info.cpp 2024-02-08T12:47:28,175 [3/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/ggml-alloc.c 2024-02-08T12:47:31,344 [4/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/ggml-backend.c 2024-02-08T12:47:35,477 [5/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/console.cpp 2024-02-08T12:47:39,046 [6/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/sampling.cpp 2024-02-08T12:47:44,196 [7/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/grammar-parser.cpp 2024-02-08T12:47:50,894 [8/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wno-cast-qual -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/llava.cpp 2024-02-08T12:47:59,626 [9/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/train.cpp 2024-02-08T12:48:02,461 [10/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/ggml-quants.c 2024-02-08T12:48:09,165 [11/22] /usr/bin/c++ -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/llava-cli.cpp 2024-02-08T12:48:19,654 [12/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/common.cpp 2024-02-08T12:48:19,654 In file included from /usr/include/c++/12/vector:70, 2024-02-08T12:48:19,655 from /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-08T12:48:19,656 from /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/sampling.h:5, 2024-02-08T12:48:19,657 from /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/common.h:7, 2024-02-08T12:48:19,658 from /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/common.cpp:1: 2024-02-08T12:48:19,659 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const llama_model_kv_override&}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-02-08T12:48:19,660 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-08T12:48:19,661 439 | vector<_Tp, _Alloc>:: 2024-02-08T12:48:19,662 | ^~~~~~~~~~~~~~~~~~~ 2024-02-08T12:48:19,663 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-02-08T12:48:19,664 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-08T12:48:19,665 In file included from /usr/include/c++/12/vector:64: 2024-02-08T12:48:19,666 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-08T12:48:19,667 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/common.cpp:850:42: 2024-02-08T12:48:19,668 /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-08T12:48:19,669 1287 | _M_realloc_insert(end(), __x); 2024-02-08T12:48:19,670 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-08T12:48:19,671 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-08T12:48:19,671 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/common/common.cpp:895:41: 2024-02-08T12:48:19,672 /usr/include/c++/12/bits/vector.tcc:123:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-08T12:48:19,673 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-02-08T12:48:19,674 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:48:33,213 [13/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/ggml.c 2024-02-08T12:48:33,459 [14/22] : && /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 && : 2024-02-08T12:48:33,622 [15/22] : && /usr/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 && : 2024-02-08T12:48:46,161 [16/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wno-cast-qual -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/examples/llava/clip.cpp 2024-02-08T12:48:46,450 [17/22] : && /usr/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 && : 2024-02-08T12:49:17,875 [18/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp 2024-02-08T12:49:17,875 In file included from /usr/include/c++/12/vector:64, 2024-02-08T12:49:17,875 from /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.h:908, 2024-02-08T12:49:17,876 from /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:2: 2024-02-08T12:49:17,876 /usr/include/c++/12/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]’: 2024-02-08T12:49:17,877 /usr/include/c++/12/bits/stl_vector.h:673:7: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,877 673 | vector(initializer_list __l, 2024-02-08T12:49:17,878 | ^~~~~~ 2024-02-08T12:49:17,878 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/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*)’: 2024-02-08T12:49:17,879 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3528:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,879 3528 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,879 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,880 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3532:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,880 3532 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,881 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,881 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3533:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,882 3533 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,883 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,883 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3563:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,883 3563 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:17,884 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,884 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3564:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,884 3564 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-08T12:49:17,885 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,885 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3565:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,885 3565 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:17,886 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,886 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3581:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,887 3581 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,887 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,888 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3583:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,888 3583 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,889 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,889 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3584:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,890 3584 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,890 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,891 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3596:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,891 3596 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:17,891 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,892 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3604:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,893 3604 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:17,893 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,893 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3609:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,894 3609 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,894 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,894 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3613:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,895 3613 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,895 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,896 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3614:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,897 3614 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:17,898 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,899 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3616:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,899 3616 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,900 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,900 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3618:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,901 3618 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-02-08T12:49:17,901 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,902 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3630:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,903 3630 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:17,903 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,904 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3633:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,905 3633 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-02-08T12:49:17,905 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,906 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3634:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,906 3634 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-02-08T12:49:17,906 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,907 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3637:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,907 3637 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T12:49:17,908 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,908 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3638:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,909 3638 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:17,910 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,910 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3641:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,911 3641 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:17,911 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,912 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3646:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,912 3646 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,913 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,913 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3647:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,914 3647 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-08T12:49:17,915 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,915 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3651:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,916 3651 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,917 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,917 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3652:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,918 3652 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:17,918 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,919 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3653:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,919 3653 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,920 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,920 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3665:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,921 3665 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T12:49:17,921 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,922 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3669:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,923 3669 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-08T12:49:17,923 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,924 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3671:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,924 3671 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:17,925 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,926 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3674:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,926 3674 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-08T12:49:17,927 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,927 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3683:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,928 3683 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,929 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,929 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3686:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,930 3686 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,930 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,931 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3687:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,931 3687 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:17,932 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,932 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3688:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,933 3688 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,933 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,934 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3698:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,934 3698 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:17,935 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,936 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3703:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,937 3703 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:17,937 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,938 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3704:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,938 3704 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-08T12:49:17,939 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,940 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3707:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,940 3707 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T12:49:17,941 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,942 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3709:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,942 3709 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:17,943 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,943 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3712:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,944 3712 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:17,944 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,945 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3715:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,945 3715 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {64}); 2024-02-08T12:49:17,946 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,946 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3716:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,947 3716 | layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias", i), {64}); 2024-02-08T12:49:17,948 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,948 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3719:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,949 3719 | layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), {64}); 2024-02-08T12:49:17,950 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,950 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3724:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,951 3724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,951 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,952 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3725:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,953 3725 | model.tok_norm = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,953 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,954 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3726:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,955 3726 | model.tok_norm_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-02-08T12:49:17,955 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,956 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3730:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,956 3730 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,957 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,957 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3731:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,958 3731 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:17,958 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,959 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3732:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,959 3732 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,960 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,961 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3741:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,961 3741 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:17,962 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,963 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3742:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,964 3742 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:17,964 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,965 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3744:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,966 3744 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T12:49:17,966 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,967 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3745:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,967 3745 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-02-08T12:49:17,968 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,969 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3748:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,969 3748 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-08T12:49:17,970 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,970 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3750:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,971 3750 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:17,971 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,971 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3754:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,972 3754 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T12:49:17,972 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,973 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3762:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,974 3762 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,975 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,975 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3766:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,976 3766 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,977 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,977 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3767:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,978 3767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,979 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,979 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3776:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,980 3776 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:17,981 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,982 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3778:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,983 3778 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T12:49:17,983 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,984 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3779:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,985 3779 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:17,985 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,986 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3786:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,986 3786 | layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false); 2024-02-08T12:49:17,987 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,988 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3791:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,989 3791 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,989 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,990 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3795:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,991 3795 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:17,991 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,992 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3796:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,993 3796 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:17,993 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,994 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3797:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,994 3797 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:17,995 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,996 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3806:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,996 3806 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:17,997 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:17,998 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3807:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:17,999 3807 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:17,999 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,000 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3809:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,000 3809 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,001 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,002 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3810:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,002 3810 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:18,003 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,004 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3816:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,005 3816 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}, false); 2024-02-08T12:49:18,006 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,006 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3820:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,007 3820 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:18,008 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,009 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3824:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,009 3824 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:18,010 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,010 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3829:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,011 3829 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,012 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,013 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3833:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,013 3833 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,014 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,014 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3834:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,015 3834 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,016 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,016 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3843:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,017 3843 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:18,017 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,018 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3846:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,019 3846 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd*3}); 2024-02-08T12:49:18,020 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,020 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3851:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,021 3851 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2}); 2024-02-08T12:49:18,022 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,022 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3853:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,023 3853 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff/2}); 2024-02-08T12:49:18,023 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,024 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3858:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,025 3858 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,025 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,026 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3862:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,027 3862 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,028 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,028 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3863:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,029 3863 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,030 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,030 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3872:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,031 3872 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:18,031 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,032 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3876:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,033 3876 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:18,033 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,034 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3877:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,035 3877 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,036 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,037 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3881:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,037 3881 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-08T12:49:18,038 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,039 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3882:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,040 3882 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-08T12:49:18,040 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,041 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3887:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,042 3887 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-08T12:49:18,042 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,043 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3893:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,043 3893 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,044 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,044 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3897:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,045 3897 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,045 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,046 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3898:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,046 3898 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:18,047 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,047 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3899:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,048 3899 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,049 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,049 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3900:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,050 3900 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-02-08T12:49:18,051 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,051 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3909:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,052 3909 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:18,053 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,053 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3910:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,054 3910 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:18,055 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,056 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3912:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,057 3912 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, false); 2024-02-08T12:49:18,057 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,058 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3916:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,059 3916 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,059 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,060 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3917:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,060 3917 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-02-08T12:49:18,061 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,062 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3919:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,062 3919 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:18,063 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,064 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3920:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,065 3920 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-08T12:49:18,066 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,067 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3922:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,067 3922 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:18,068 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,069 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3923:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,070 3923 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-08T12:49:18,070 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,071 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3926:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,072 3926 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,074 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,075 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3929:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,076 3929 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-08T12:49:18,077 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,078 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3930:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,079 3930 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T12:49:18,080 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,081 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3933:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,082 3933 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-08T12:49:18,084 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,085 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3938:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,086 3938 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,086 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,087 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3942:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,088 3942 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,089 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,090 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3943:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,090 3943 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,091 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,092 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3952:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,093 3952 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T12:49:18,094 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,095 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3954:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,095 3954 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,096 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,096 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3955:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,097 3955 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:18,098 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,098 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3959:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,099 3959 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-08T12:49:18,099 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,100 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3966:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,101 3966 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,102 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,102 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3967:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,103 3967 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-08T12:49:18,104 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,105 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3971:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,106 3971 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,107 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,108 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3972:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,109 3972 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:18,111 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,112 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3973:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,114 3973 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,115 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,116 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3988:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,116 3988 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,117 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,117 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:3998:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,118 3998 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-08T12:49:18,118 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,119 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4003:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,119 4003 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,120 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,120 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4007:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,121 4007 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,122 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,123 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4008:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,123 4008 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:18,124 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,125 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4009:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,125 4009 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,126 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,126 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4019:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,127 4019 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T12:49:18,128 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,128 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4024:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,129 4024 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T12:49:18,129 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,130 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4031:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,130 4031 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T12:49:18,131 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,131 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4039:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,131 4039 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,132 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,133 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4041:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,133 4041 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,134 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,134 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4042:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,135 4042 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T12:49:18,136 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,136 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4043:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,137 4043 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,138 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,138 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4055:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,139 4055 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T12:49:18,139 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,140 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4069:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,141 4069 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,141 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,142 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4073:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,142 4073 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T12:49:18,143 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,143 /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/vendor/llama.cpp/llama.cpp:4074:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T12:49:18,144 4074 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T12:49:18,145 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,145 In file included from /usr/include/c++/12/vector:70: 2024-02-08T12:49:18,146 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const double&}; _Tp = double; _Alloc = std::allocator]’: 2024-02-08T12:49:18,147 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-08T12:49:18,147 439 | vector<_Tp, _Alloc>:: 2024-02-08T12:49:18,148 | ^~~~~~~~~~~~~~~~~~~ 2024-02-08T12:49:18,149 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-08T12:49:18,150 inlined from ‘std::back_insert_iterator<_Container>& std::back_insert_iterator<_Container>::operator=(const typename _Container::value_type&) [with _Container = std::vector]’ at /usr/include/c++/12/bits/stl_iterator.h:735:22, 2024-02-08T12:49:18,150 inlined from ‘_OutputIterator std::partial_sum(_InputIterator, _InputIterator, _OutputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; _OutputIterator = back_insert_iterator >]’ at /usr/include/c++/12/bits/stl_numeric.h:270:17, 2024-02-08T12:49:18,151 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-08T12:49:18,152 /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-08T12:49:18,153 1287 | _M_realloc_insert(end(), __x); 2024-02-08T12:49:18,154 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-08T12:49:18,154 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-08T12:49:18,155 inlined from ‘std::back_insert_iterator<_Container>& std::back_insert_iterator<_Container>::operator=(const typename _Container::value_type&) [with _Container = std::vector]’ at /usr/include/c++/12/bits/stl_iterator.h:735:22, 2024-02-08T12:49:18,156 inlined from ‘_OutputIterator std::partial_sum(_InputIterator, _InputIterator, _OutputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; _OutputIterator = back_insert_iterator >]’ at /usr/include/c++/12/bits/stl_numeric.h:274:16, 2024-02-08T12:49:18,157 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-08T12:49:18,158 /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-08T12:49:18,159 1287 | _M_realloc_insert(end(), __x); 2024-02-08T12:49:18,159 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-08T12:49:18,270 [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 && : 2024-02-08T12:49:18,578 [20/22] : && /usr/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 && : 2024-02-08T12:49:18,617 [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/tmp8b630dc1/build/vendor/llama.cpp: vendor/llama.cpp/libllama.so && : 2024-02-08T12:49:18,908 [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/tmp8b630dc1/build/vendor/llama.cpp: vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.so && : 2024-02-08T12:49:18,912 *** Installing project into wheel... 2024-02-08T12:49:18,950 -- Install configuration: "Release" 2024-02-08T12:49:18,953 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/lib/libggml_shared.so 2024-02-08T12:49:18,997 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-02-08T12:49:19,000 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-02-08T12:49:19,003 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/include/ggml.h 2024-02-08T12:49:19,007 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/include/ggml-alloc.h 2024-02-08T12:49:19,009 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/include/ggml-backend.h 2024-02-08T12:49:19,012 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/lib/libllama.so 2024-02-08T12:49:19,084 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/include/llama.h 2024-02-08T12:49:19,090 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/bin/convert.py 2024-02-08T12:49:19,094 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/bin/convert-lora-to-ggml.py 2024-02-08T12:49:19,103 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/llama_core/libllama.so 2024-02-08T12:49:19,172 -- Installing: /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/llama_core/libllama.so 2024-02-08T12:49:19,243 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/lib/libllava.so 2024-02-08T12:49:19,264 -- Set runtime path of "/tmp/tmp8b630dc1/wheel/platlib/lib/libllava.so" to "" 2024-02-08T12:49:19,307 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/bin/llava-cli 2024-02-08T12:49:19,320 -- Set runtime path of "/tmp/tmp8b630dc1/wheel/platlib/bin/llava-cli" to "" 2024-02-08T12:49:19,349 -- Installing: /tmp/tmp8b630dc1/wheel/platlib/llama_core/libllava.so 2024-02-08T12:49:19,369 -- Set runtime path of "/tmp/tmp8b630dc1/wheel/platlib/llama_core/libllava.so" to "" 2024-02-08T12:49:19,409 -- Installing: /tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/llama_core/libllava.so 2024-02-08T12:49:19,427 -- Set runtime path of "/tmp/pip-wheel-3oti5nny/llama-core_0613c40730394636bda3af39ede0592a/llama_core/libllava.so" to "" 2024-02-08T12:49:19,477 *** Making wheel... 2024-02-08T12:49:20,800 *** Created llama_core-0.0.1-cp311-cp311-manylinux_2_36_armv7l.whl... 2024-02-08T12:49:20,858 Building wheel for llama-core (pyproject.toml): finished with status 'done' 2024-02-08T12:49:20,886 Created wheel for llama-core: filename=llama_core-0.0.1-cp311-cp311-manylinux_2_36_armv7l.whl size=2356113 sha256=0457a9c9fad48014762fe5e8eaacf08e7a030a8fa375ced00308fc00a32294d5 2024-02-08T12:49:20,887 Stored in directory: /tmp/pip-ephem-wheel-cache-byfd2sgw/wheels/7f/ed/08/3e0a91ffced4ee25fd687c762974723f58f792ee58aef4e881 2024-02-08T12:49:20,899 Successfully built llama-core 2024-02-08T12:49:20,958 Removed build tracker: '/tmp/pip-build-tracker-jndmbokv'