2024-02-09T02:46:32,977 Created temporary directory: /tmp/pip-build-tracker-338z29lg 2024-02-09T02:46:32,978 Initialized build tracking at /tmp/pip-build-tracker-338z29lg 2024-02-09T02:46:32,978 Created build tracker: /tmp/pip-build-tracker-338z29lg 2024-02-09T02:46:32,979 Entered build tracker: /tmp/pip-build-tracker-338z29lg 2024-02-09T02:46:32,980 Created temporary directory: /tmp/pip-wheel-r6o2nt2w 2024-02-09T02:46:32,983 Created temporary directory: /tmp/pip-ephem-wheel-cache-x06ivbyi 2024-02-09T02:46:33,006 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-09T02:46:33,009 2 location(s) to search for versions of llama-core: 2024-02-09T02:46:33,009 * https://pypi.org/simple/llama-core/ 2024-02-09T02:46:33,009 * https://www.piwheels.org/simple/llama-core/ 2024-02-09T02:46:33,010 Fetching project page and analyzing links: https://pypi.org/simple/llama-core/ 2024-02-09T02:46:33,011 Getting page https://pypi.org/simple/llama-core/ 2024-02-09T02:46:33,012 Found index url https://pypi.org/simple/ 2024-02-09T02:46:33,228 Fetched page https://pypi.org/simple/llama-core/ as application/vnd.pypi.simple.v1+json 2024-02-09T02:46:33,230 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) 2024-02-09T02:46:33,231 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 2024-02-09T02:46:33,232 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) 2024-02-09T02:46:33,232 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) 2024-02-09T02:46:33,233 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 2024-02-09T02:46:33,234 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/16/8f/8bdffd743f5b585d172348cb0b4898599d502dcc4ca9776d1d59ddf04b0f/llama_core-0.0.3-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T02:46:33,235 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/5b/40/9058f432251845d67ea827068977a063ab628a9f20770c6d993705bef6ab/llama_core-0.0.3-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T02:46:33,236 Found link https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.3 2024-02-09T02:46:33,236 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-core/ 2024-02-09T02:46:33,237 Getting page https://www.piwheels.org/simple/llama-core/ 2024-02-09T02:46:33,238 Found index url https://www.piwheels.org/simple/ 2024-02-09T02:46:33,394 Fetched page https://www.piwheels.org/simple/llama-core/ as text/html 2024-02-09T02:46:33,397 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.2-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=39b6da3d8b2c0a1bf4fe8ea9c6e0c25dc5ee291ba2d893e01751a684696ada6f (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T02:46:33,398 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.2-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=80df05f3984df31d62d543508bcf72719f7819fc924f4fe4aa2b8a14a3151fb5 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T02:46:33,398 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.1-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=0457a9c9fad48014762fe5e8eaacf08e7a030a8fa375ced00308fc00a32294d5 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T02:46:33,399 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.1-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=77646f382b23fba3fee5b1c6ca2af87609b49328e9c70e637104fb842bd80805 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-09T02:46:33,399 Skipping link: not a file: https://www.piwheels.org/simple/llama-core/ 2024-02-09T02:46:33,400 Skipping link: not a file: https://pypi.org/simple/llama-core/ 2024-02-09T02:46:33,418 Given no hashes to check 1 links for project 'llama-core': discarding no candidates 2024-02-09T02:46:33,436 Collecting llama-core==0.0.3 2024-02-09T02:46:33,438 Created temporary directory: /tmp/pip-unpack-u5oiejx3 2024-02-09T02:46:33,721 Downloading llama_core-0.0.3.tar.gz (10.6 MB) 2024-02-09T02:46:38,059 Added llama-core==0.0.3 from https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz to build tracker '/tmp/pip-build-tracker-338z29lg' 2024-02-09T02:46:38,064 Created temporary directory: /tmp/pip-build-env-yvginwh7 2024-02-09T02:46:38,071 Installing build dependencies: started 2024-02-09T02:46:38,073 Running command pip subprocess to install build dependencies 2024-02-09T02:46:39,314 Using pip 23.3.1 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11) 2024-02-09T02:46:39,838 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-09T02:46:40,282 Collecting scikit-build-core[pyproject] 2024-02-09T02:46:40,316 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.0-py3-none-any.whl (139 kB) 2024-02-09T02:46:40,618 Collecting packaging>=20.9 (from scikit-build-core[pyproject]) 2024-02-09T02:46:40,632 Using cached https://www.piwheels.org/simple/packaging/packaging-23.2-py3-none-any.whl (53 kB) 2024-02-09T02:46:40,736 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]) 2024-02-09T02:46:40,750 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-02-09T02:46:40,821 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]) 2024-02-09T02:46:40,836 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-02-09T02:46:43,443 Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata 2024-02-09T02:46:44,138 Successfully installed packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.0 2024-02-09T02:46:44,464 [notice] A new release of pip is available: 23.3.1 -> 24.0 2024-02-09T02:46:44,465 [notice] To update, run: python3 -m pip install --upgrade pip 2024-02-09T02:46:44,728 Installing build dependencies: finished with status 'done' 2024-02-09T02:46:44,731 Getting requirements to build wheel: started 2024-02-09T02:46:44,732 Running command Getting requirements to build wheel 2024-02-09T02:46:45,160 Getting requirements to build wheel: finished with status 'done' 2024-02-09T02:46:45,185 Created temporary directory: /tmp/pip-modern-metadata-xv3zbigm 2024-02-09T02:46:45,187 Preparing metadata (pyproject.toml): started 2024-02-09T02:46:45,188 Running command Preparing metadata (pyproject.toml) 2024-02-09T02:46:45,687 *** scikit-build-core 0.8.0 using CMake 3.25.1 (metadata_wheel) 2024-02-09T02:46:45,774 Preparing metadata (pyproject.toml): finished with status 'done' 2024-02-09T02:46:45,779 Source in /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836 has version 0.0.3, which satisfies requirement llama-core==0.0.3 from https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz 2024-02-09T02:46:45,780 Removed llama-core==0.0.3 from https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz from build tracker '/tmp/pip-build-tracker-338z29lg' 2024-02-09T02:46:45,784 Created temporary directory: /tmp/pip-unpack-1p8dy0so 2024-02-09T02:46:45,785 Created temporary directory: /tmp/pip-unpack-6d1rp1m8 2024-02-09T02:46:45,792 Building wheels for collected packages: llama-core 2024-02-09T02:46:45,799 Created temporary directory: /tmp/pip-wheel-af79lhsd 2024-02-09T02:46:45,800 Destination directory: /tmp/pip-wheel-af79lhsd 2024-02-09T02:46:45,802 Building wheel for llama-core (pyproject.toml): started 2024-02-09T02:46:45,803 Running command Building wheel for llama-core (pyproject.toml) 2024-02-09T02:46:46,292 *** scikit-build-core 0.8.0 using CMake 3.25.1 (wheel) 2024-02-09T02:46:46,311 *** Configuring CMake... 2024-02-09T02:46:46,424 loading initial cache file /tmp/tmp6nkojmzs/build/CMakeInit.txt 2024-02-09T02:46:46,740 -- The C compiler identification is GNU 12.2.0 2024-02-09T02:46:47,092 -- The CXX compiler identification is GNU 12.2.0 2024-02-09T02:46:47,153 -- Detecting C compiler ABI info 2024-02-09T02:46:47,455 -- Detecting C compiler ABI info - done 2024-02-09T02:46:47,498 -- Check for working C compiler: /usr/bin/cc - skipped 2024-02-09T02:46:47,500 -- Detecting C compile features 2024-02-09T02:46:47,503 -- Detecting C compile features - done 2024-02-09T02:46:47,527 -- Detecting CXX compiler ABI info 2024-02-09T02:46:47,899 -- Detecting CXX compiler ABI info - done 2024-02-09T02:46:47,943 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-02-09T02:46:47,945 -- Detecting CXX compile features 2024-02-09T02:46:47,949 -- Detecting CXX compile features - done 2024-02-09T02:46:47,984 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-09T02:46:48,059 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-02-09T02:46:48,425 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-02-09T02:46:48,430 -- Found Threads: TRUE 2024-02-09T02:46:48,440 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-02-09T02:46:48,557 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-02-09T02:46:48,557 -- ARM detected 2024-02-09T02:46:48,560 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-02-09T02:46:48,923 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-02-09T02:46:48,969 CMake Warning (dev) at CMakeLists.txt:17 (install): 2024-02-09T02:46:48,970 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-09T02:46:48,970 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-09T02:46:48,973 CMake Warning (dev) at CMakeLists.txt:25 (install): 2024-02-09T02:46:48,973 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-09T02:46:48,974 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-09T02:46:48,980 -- Configuring done 2024-02-09T02:46:49,059 -- Generating done 2024-02-09T02:46:49,078 -- Build files have been written to: /tmp/tmp6nkojmzs/build 2024-02-09T02:46:49,091 *** Building project with Ninja... 2024-02-09T02:46:49,480 [1/22] cd /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-02-09T02:46:49,481 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-09T02:46:49,700 [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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/build-info.cpp 2024-02-09T02:46:52,797 [3/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/ggml-alloc.c 2024-02-09T02:46:58,497 [4/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/ggml-backend.c 2024-02-09T02:47:03,998 [5/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/console.cpp 2024-02-09T02:47:07,197 [6/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/sampling.cpp 2024-02-09T02:47:17,411 [7/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/grammar-parser.cpp 2024-02-09T02:47:23,807 [8/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/train.cpp 2024-02-09T02:47:24,767 [9/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/llava.cpp 2024-02-09T02:47:27,259 [10/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/ggml-quants.c 2024-02-09T02:47:34,968 [11/22] /usr/bin/c++ -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/llava-cli.cpp 2024-02-09T02:47:47,116 [12/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/common.cpp 2024-02-09T02:47:47,117 In file included from /usr/include/c++/12/vector:70, 2024-02-09T02:47:47,117 from /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-09T02:47:47,118 from /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/sampling.h:5, 2024-02-09T02:47:47,119 from /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/common.h:7, 2024-02-09T02:47:47,120 from /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/common.cpp:1: 2024-02-09T02:47:47,121 /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]’: 2024-02-09T02:47:47,122 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-09T02:47:47,123 439 | vector<_Tp, _Alloc>:: 2024-02-09T02:47:47,123 | ^~~~~~~~~~~~~~~~~~~ 2024-02-09T02:47:47,124 /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]’: 2024-02-09T02:47:47,125 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-09T02:47:47,126 In file included from /usr/include/c++/12/vector:64: 2024-02-09T02:47:47,127 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-09T02:47:47,128 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/common.cpp:850:42: 2024-02-09T02:47:47,129 /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 2024-02-09T02:47:47,130 1287 | _M_realloc_insert(end(), __x); 2024-02-09T02:47:47,131 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-09T02:47:47,132 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-09T02:47:47,133 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/common/common.cpp:895:41: 2024-02-09T02:47:47,134 /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 2024-02-09T02:47:47,135 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-02-09T02:47:47,136 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:00,228 [13/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/ggml.c 2024-02-09T02:48:00,451 [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 && : 2024-02-09T02:48:00,596 [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 && : 2024-02-09T02:48:16,105 [16/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/examples/llava/clip.cpp 2024-02-09T02:48:16,394 [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 && : 2024-02-09T02:48:46,158 [18/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp 2024-02-09T02:48:46,159 In file included from /usr/include/c++/12/vector:64, 2024-02-09T02:48:46,159 from /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.h:908, 2024-02-09T02:48:46,160 from /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:2: 2024-02-09T02:48:46,160 /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]’: 2024-02-09T02:48:46,161 /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 2024-02-09T02:48:46,161 673 | vector(initializer_list __l, 2024-02-09T02:48:46,162 | ^~~~~~ 2024-02-09T02:48:46,162 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/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*)’: 2024-02-09T02:48:46,162 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3528:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,163 3528 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,163 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,163 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3532:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,164 3532 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,164 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,165 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3533:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,165 3533 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,166 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,166 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3563:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,167 3563 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,167 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,168 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3564:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,168 3564 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-09T02:48:46,169 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,169 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3565:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,170 3565 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,170 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,171 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3581:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,171 3581 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,172 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,172 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3583:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,173 3583 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,173 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,173 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3584:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,174 3584 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,174 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,174 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3596:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,175 3596 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,176 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,176 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3604:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,177 3604 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,177 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,178 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3609:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,178 3609 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,179 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,179 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3613:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,180 3613 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,180 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,181 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3614:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,182 3614 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,183 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,184 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3616:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,184 3616 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,185 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,185 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3618:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,186 3618 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-02-09T02:48:46,186 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,187 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3630:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,187 3630 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,188 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,188 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3633:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,189 3633 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-02-09T02:48:46,189 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,190 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3634:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,191 3634 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-02-09T02:48:46,191 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,192 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3637:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,192 3637 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-09T02:48:46,193 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,193 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3638:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,194 3638 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,195 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,195 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3641:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,196 3641 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,196 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,197 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3646:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,197 3646 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,198 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,198 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3647:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,199 3647 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-09T02:48:46,199 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,200 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3651:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,200 3651 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,201 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,201 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3652:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,202 3652 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,203 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,203 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3653:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,204 3653 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,204 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,205 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3665:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,205 3665 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-09T02:48:46,206 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,207 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3669:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,207 3669 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-09T02:48:46,208 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,208 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3671:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,208 3671 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,209 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,210 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3674:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,210 3674 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-09T02:48:46,211 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,212 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3683:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,212 3683 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,213 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,213 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3686:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,214 3686 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,215 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,215 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3687:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,216 3687 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,216 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,217 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3688:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,217 3688 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,218 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,219 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3698:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,220 3698 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,220 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,221 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3703:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,222 3703 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,222 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,223 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3704:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,223 3704 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-09T02:48:46,223 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,224 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3707:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,225 3707 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-09T02:48:46,225 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,226 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3709:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,227 3709 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,227 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,228 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3712:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,229 3712 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,229 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,230 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3715:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,230 3715 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {64}); 2024-02-09T02:48:46,231 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,232 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3716:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,232 3716 | layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias", i), {64}); 2024-02-09T02:48:46,233 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,234 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3719:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,234 3719 | layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), {64}); 2024-02-09T02:48:46,234 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,235 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3724:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,235 3724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,236 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,236 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3725:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,237 3725 | model.tok_norm = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,237 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,238 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3726:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,239 3726 | model.tok_norm_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,239 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,240 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3730:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,241 3730 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,241 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,242 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3731:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,243 3731 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,243 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,244 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3732:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,244 3732 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,245 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,246 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3741:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,247 3741 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,247 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,247 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3742:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,248 3742 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,248 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,249 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3744:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,249 3744 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-09T02:48:46,250 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,250 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3745:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,251 3745 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-02-09T02:48:46,252 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,252 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3748:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,253 3748 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-09T02:48:46,254 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,254 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3750:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,255 3750 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,256 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,256 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3754:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,257 3754 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-09T02:48:46,258 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,258 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3762:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,259 3762 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,260 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,260 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3766:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,261 3766 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,261 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,262 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3767:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,262 3767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,263 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,263 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3776:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,264 3776 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,264 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,265 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3778:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,266 3778 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-09T02:48:46,266 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,267 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3779:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,268 3779 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,269 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,269 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3786:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,270 3786 | layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false); 2024-02-09T02:48:46,271 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,271 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3791:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,272 3791 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,274 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,274 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3795:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,275 3795 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,275 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,276 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3796:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,277 3796 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,277 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,278 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3797:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,279 3797 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,279 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,280 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3806:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,281 3806 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,281 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,282 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3807:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,283 3807 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,284 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,284 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3809:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,285 3809 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,286 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,286 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3810:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,287 3810 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,288 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,288 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3816:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,289 3816 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}, false); 2024-02-09T02:48:46,290 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,290 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3820:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,291 3820 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,291 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,292 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3824:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,293 3824 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,293 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,294 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3829:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,295 3829 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,296 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,297 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3833:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,297 3833 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,298 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,299 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3834:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,300 3834 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,301 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,301 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3843:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,302 3843 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,302 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,303 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3846:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,304 3846 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd*3}); 2024-02-09T02:48:46,305 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,305 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3851:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,305 3851 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2}); 2024-02-09T02:48:46,306 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,306 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3853:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,307 3853 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff/2}); 2024-02-09T02:48:46,308 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,308 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3858:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,309 3858 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,310 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,310 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3862:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,311 3862 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,312 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,313 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3863:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,313 3863 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,314 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,315 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3872:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,315 3872 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,316 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,316 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3876:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,317 3876 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,318 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,319 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3877:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,319 3877 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,320 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,320 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3881:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,321 3881 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-09T02:48:46,321 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,322 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3882:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,322 3882 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-09T02:48:46,323 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,324 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3887:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,324 3887 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-09T02:48:46,325 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,326 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3893:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,327 3893 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,328 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,328 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3897:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,329 3897 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,330 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,330 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3898:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,331 3898 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,332 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,333 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3899:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,334 3899 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,334 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,334 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3900:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,335 3900 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-02-09T02:48:46,335 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,336 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3909:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,336 3909 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,337 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,337 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3910:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,338 3910 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,338 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,339 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3912:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,340 3912 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, false); 2024-02-09T02:48:46,340 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,341 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3916:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,342 3916 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,342 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,343 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3917:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,343 3917 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-02-09T02:48:46,344 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,345 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3919:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,345 3919 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,346 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,347 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3920:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,347 3920 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-09T02:48:46,347 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,348 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3922:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,349 3922 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,349 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,350 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3923:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,350 3923 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-09T02:48:46,351 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,352 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3926:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,352 3926 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,353 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,354 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3929:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,355 3929 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-09T02:48:46,356 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,356 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3930:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,357 3930 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-09T02:48:46,358 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,358 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3933:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,359 3933 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-09T02:48:46,360 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,361 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3938:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,362 3938 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,362 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,363 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3942:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,363 3942 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,364 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,364 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3943:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,365 3943 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,365 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,366 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3952:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,367 3952 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-09T02:48:46,367 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,368 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3954:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,369 3954 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,370 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,370 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3955:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,371 3955 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,372 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,373 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3959:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,373 3959 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-09T02:48:46,374 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,376 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3966:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,376 3966 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,378 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,378 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3967:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,379 3967 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-09T02:48:46,380 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,381 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3971:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,381 3971 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,382 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,383 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3972:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,384 3972 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,384 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,385 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3973:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,386 3973 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,387 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,388 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3988:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,388 3988 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,389 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,390 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:3998:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,390 3998 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-09T02:48:46,391 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,392 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4003:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,393 4003 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,393 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,394 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4007:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,395 4007 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,395 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,396 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4008:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,397 4008 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,397 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,398 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4009:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,398 4009 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,399 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,400 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4019:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,401 4019 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-09T02:48:46,401 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,402 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4024:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,403 4024 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-09T02:48:46,404 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,405 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4031:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,405 4031 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-09T02:48:46,406 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,407 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4039:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,407 4039 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,409 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,410 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4041:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,412 4041 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,413 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,414 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4042:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,415 4042 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-09T02:48:46,416 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,417 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4043:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,418 4043 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,419 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,420 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4055:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,420 4055 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-09T02:48:46,421 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,421 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4069:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,422 4069 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,422 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,423 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4073:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,424 4073 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-09T02:48:46,425 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,425 /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/vendor/llama.cpp/llama.cpp:4074:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-09T02:48:46,426 4074 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-09T02:48:46,427 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,428 In file included from /usr/include/c++/12/vector:70: 2024-02-09T02:48:46,428 /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]’: 2024-02-09T02:48:46,429 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-09T02:48:46,430 439 | vector<_Tp, _Alloc>:: 2024-02-09T02:48:46,430 | ^~~~~~~~~~~~~~~~~~~ 2024-02-09T02:48:46,431 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-09T02:48:46,431 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, 2024-02-09T02:48:46,432 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, 2024-02-09T02:48:46,432 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-09T02:48:46,432 /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 2024-02-09T02:48:46,433 1287 | _M_realloc_insert(end(), __x); 2024-02-09T02:48:46,433 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-09T02:48:46,434 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-09T02:48:46,434 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, 2024-02-09T02:48:46,435 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, 2024-02-09T02:48:46,436 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-09T02:48:46,437 /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 2024-02-09T02:48:46,437 1287 | _M_realloc_insert(end(), __x); 2024-02-09T02:48:46,438 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-09T02:48:46,576 [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 && : 2024-02-09T02:48:46,874 [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 && : 2024-02-09T02:48:46,941 [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/tmp6nkojmzs/build/vendor/llama.cpp: vendor/llama.cpp/libllama.so && : 2024-02-09T02:48:47,186 [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/tmp6nkojmzs/build/vendor/llama.cpp: vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.so && : 2024-02-09T02:48:47,191 *** Installing project into wheel... 2024-02-09T02:48:47,229 -- Install configuration: "Release" 2024-02-09T02:48:47,233 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/lib/libggml_shared.so 2024-02-09T02:48:47,277 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-02-09T02:48:47,280 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-02-09T02:48:47,284 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/include/ggml.h 2024-02-09T02:48:47,288 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/include/ggml-alloc.h 2024-02-09T02:48:47,291 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/include/ggml-backend.h 2024-02-09T02:48:47,293 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/lib/libllama.so 2024-02-09T02:48:47,360 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/include/llama.h 2024-02-09T02:48:47,365 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/bin/convert.py 2024-02-09T02:48:47,369 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/bin/convert-lora-to-ggml.py 2024-02-09T02:48:47,374 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/llama_core/libllama.so 2024-02-09T02:48:47,443 -- Installing: /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/llama_core/libllama.so 2024-02-09T02:48:47,512 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/lib/libllava.so 2024-02-09T02:48:47,532 -- Set runtime path of "/tmp/tmp6nkojmzs/wheel/platlib/lib/libllava.so" to "" 2024-02-09T02:48:47,575 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/bin/llava-cli 2024-02-09T02:48:47,588 -- Set runtime path of "/tmp/tmp6nkojmzs/wheel/platlib/bin/llava-cli" to "" 2024-02-09T02:48:47,614 -- Installing: /tmp/tmp6nkojmzs/wheel/platlib/llama_core/libllava.so 2024-02-09T02:48:47,640 -- Set runtime path of "/tmp/tmp6nkojmzs/wheel/platlib/llama_core/libllava.so" to "" 2024-02-09T02:48:47,683 -- Installing: /tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/llama_core/libllava.so 2024-02-09T02:48:47,709 -- Set runtime path of "/tmp/pip-wheel-r6o2nt2w/llama-core_3b1e0cf72eeb4bf8ab3c918700829836/llama_core/libllava.so" to "" 2024-02-09T02:48:47,753 *** Making wheel... 2024-02-09T02:48:49,041 *** Created llama_core-0.0.3-cp311-cp311-manylinux_2_36_armv7l.whl... 2024-02-09T02:48:49,098 Building wheel for llama-core (pyproject.toml): finished with status 'done' 2024-02-09T02:48:49,126 Created wheel for llama-core: filename=llama_core-0.0.3-cp311-cp311-manylinux_2_36_armv7l.whl size=2355712 sha256=60e4da9a7c59f727c521b26a7e2959af9d5e84a96fe28d9c5e31f658b74bc683 2024-02-09T02:48:49,128 Stored in directory: /tmp/pip-ephem-wheel-cache-x06ivbyi/wheels/81/85/59/2d9e60526d08156da43dae176de6f71bb0806a0348f34c3dde 2024-02-09T02:48:49,139 Successfully built llama-core 2024-02-09T02:48:49,198 Removed build tracker: '/tmp/pip-build-tracker-338z29lg'