2024-02-08T13:48:52,337 Created temporary directory: /tmp/pip-build-tracker-om9154xw 2024-02-08T13:48:52,338 Initialized build tracking at /tmp/pip-build-tracker-om9154xw 2024-02-08T13:48:52,339 Created build tracker: /tmp/pip-build-tracker-om9154xw 2024-02-08T13:48:52,339 Entered build tracker: /tmp/pip-build-tracker-om9154xw 2024-02-08T13:48:52,340 Created temporary directory: /tmp/pip-wheel-jduvmrg5 2024-02-08T13:48:52,343 Created temporary directory: /tmp/pip-ephem-wheel-cache-hl1dh2pe 2024-02-08T13:48:52,365 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-08T13:48:52,369 2 location(s) to search for versions of llama-core: 2024-02-08T13:48:52,369 * https://pypi.org/simple/llama-core/ 2024-02-08T13:48:52,369 * https://www.piwheels.org/simple/llama-core/ 2024-02-08T13:48:52,369 Fetching project page and analyzing links: https://pypi.org/simple/llama-core/ 2024-02-08T13:48:52,371 Getting page https://pypi.org/simple/llama-core/ 2024-02-08T13:48:52,372 Found index url https://pypi.org/simple/ 2024-02-08T13:48:52,536 Fetched page https://pypi.org/simple/llama-core/ as application/vnd.pypi.simple.v1+json 2024-02-08T13:48:52,538 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) 2024-02-08T13:48:52,539 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 2024-02-08T13:48:52,539 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) 2024-02-08T13:48:52,540 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) 2024-02-08T13:48:52,541 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 2024-02-08T13:48:52,541 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-core/ 2024-02-08T13:48:52,542 Getting page https://www.piwheels.org/simple/llama-core/ 2024-02-08T13:48:52,543 Found index url https://www.piwheels.org/simple/ 2024-02-08T13:48:52,710 Fetched page https://www.piwheels.org/simple/llama-core/ as text/html 2024-02-08T13:48:52,711 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) 2024-02-08T13:48:52,712 Skipping link: not a file: https://www.piwheels.org/simple/llama-core/ 2024-02-08T13:48:52,713 Skipping link: not a file: https://pypi.org/simple/llama-core/ 2024-02-08T13:48:52,733 Given no hashes to check 1 links for project 'llama-core': discarding no candidates 2024-02-08T13:48:52,752 Collecting llama-core==0.0.2 2024-02-08T13:48:52,755 Created temporary directory: /tmp/pip-unpack-93w2z2vs 2024-02-08T13:48:52,969 Downloading llama_core-0.0.2.tar.gz (10.6 MB) 2024-02-08T13:48:56,074 Added llama-core==0.0.2 from https://files.pythonhosted.org/packages/13/e0/942cd90aa6099469476699a34730f93ae98eec75637bcaaae05f30b671e5/llama_core-0.0.2.tar.gz to build tracker '/tmp/pip-build-tracker-om9154xw' 2024-02-08T13:48:56,078 Created temporary directory: /tmp/pip-build-env-s6oe6ydy 2024-02-08T13:48:56,083 Installing build dependencies: started 2024-02-08T13:48:56,084 Running command pip subprocess to install build dependencies 2024-02-08T13:48:57,223 Using pip 23.3.1 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11) 2024-02-08T13:48:57,857 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-08T13:48:58,577 Collecting scikit-build-core[pyproject] 2024-02-08T13:48:58,637 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.0-py3-none-any.whl (139 kB) 2024-02-08T13:48:58,996 Collecting packaging>=20.9 (from scikit-build-core[pyproject]) 2024-02-08T13:48:59,012 Using cached https://www.piwheels.org/simple/packaging/packaging-23.2-py3-none-any.whl (53 kB) 2024-02-08T13:48:59,340 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]) 2024-02-08T13:48:59,356 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-02-08T13:48:59,445 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]) 2024-02-08T13:48:59,469 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-02-08T13:49:03,006 Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata 2024-02-08T13:49:03,694 Successfully installed packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.0 2024-02-08T13:49:04,165 [notice] A new release of pip is available: 23.3.1 -> 24.0 2024-02-08T13:49:04,165 [notice] To update, run: python3 -m pip install --upgrade pip 2024-02-08T13:49:04,399 Installing build dependencies: finished with status 'done' 2024-02-08T13:49:04,402 Getting requirements to build wheel: started 2024-02-08T13:49:04,403 Running command Getting requirements to build wheel 2024-02-08T13:49:04,843 Getting requirements to build wheel: finished with status 'done' 2024-02-08T13:49:04,868 Created temporary directory: /tmp/pip-modern-metadata-68x_yd7l 2024-02-08T13:49:04,870 Preparing metadata (pyproject.toml): started 2024-02-08T13:49:04,871 Running command Preparing metadata (pyproject.toml) 2024-02-08T13:49:05,371 *** scikit-build-core 0.8.0 using CMake 3.25.1 (metadata_wheel) 2024-02-08T13:49:05,457 Preparing metadata (pyproject.toml): finished with status 'done' 2024-02-08T13:49:05,461 Source in /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5 has version 0.0.2, which satisfies requirement llama-core==0.0.2 from https://files.pythonhosted.org/packages/13/e0/942cd90aa6099469476699a34730f93ae98eec75637bcaaae05f30b671e5/llama_core-0.0.2.tar.gz 2024-02-08T13:49:05,462 Removed llama-core==0.0.2 from https://files.pythonhosted.org/packages/13/e0/942cd90aa6099469476699a34730f93ae98eec75637bcaaae05f30b671e5/llama_core-0.0.2.tar.gz from build tracker '/tmp/pip-build-tracker-om9154xw' 2024-02-08T13:49:05,467 Created temporary directory: /tmp/pip-unpack-ylne5wlb 2024-02-08T13:49:05,468 Created temporary directory: /tmp/pip-unpack-v_5ofgxu 2024-02-08T13:49:05,475 Building wheels for collected packages: llama-core 2024-02-08T13:49:05,479 Created temporary directory: /tmp/pip-wheel-korl_nr3 2024-02-08T13:49:05,480 Destination directory: /tmp/pip-wheel-korl_nr3 2024-02-08T13:49:05,482 Building wheel for llama-core (pyproject.toml): started 2024-02-08T13:49:05,483 Running command Building wheel for llama-core (pyproject.toml) 2024-02-08T13:49:05,986 *** scikit-build-core 0.8.0 using CMake 3.25.1 (wheel) 2024-02-08T13:49:06,006 *** Configuring CMake... 2024-02-08T13:49:06,107 loading initial cache file /tmp/tmp6p3xbct_/build/CMakeInit.txt 2024-02-08T13:49:06,387 -- The C compiler identification is GNU 12.2.0 2024-02-08T13:49:06,711 -- The CXX compiler identification is GNU 12.2.0 2024-02-08T13:49:06,790 -- Detecting C compiler ABI info 2024-02-08T13:49:07,054 -- Detecting C compiler ABI info - done 2024-02-08T13:49:07,092 -- Check for working C compiler: /usr/bin/cc - skipped 2024-02-08T13:49:07,093 -- Detecting C compile features 2024-02-08T13:49:07,096 -- Detecting C compile features - done 2024-02-08T13:49:07,115 -- Detecting CXX compiler ABI info 2024-02-08T13:49:07,438 -- Detecting CXX compiler ABI info - done 2024-02-08T13:49:07,476 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-02-08T13:49:07,478 -- Detecting CXX compile features 2024-02-08T13:49:07,480 -- Detecting CXX compile features - done 2024-02-08T13:49:07,518 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-08T13:49:07,600 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-02-08T13:49:07,920 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-02-08T13:49:07,925 -- Found Threads: TRUE 2024-02-08T13:49:07,934 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-02-08T13:49:08,035 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-02-08T13:49:08,035 -- ARM detected 2024-02-08T13:49:08,038 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-02-08T13:49:08,355 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-02-08T13:49:08,384 CMake Warning (dev) at CMakeLists.txt:19 (install): 2024-02-08T13:49:08,384 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-08T13:49:08,385 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-08T13:49:08,386 CMake Warning (dev) at CMakeLists.txt:28 (install): 2024-02-08T13:49:08,386 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-08T13:49:08,387 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-08T13:49:08,392 -- Configuring done 2024-02-08T13:49:08,494 -- Generating done 2024-02-08T13:49:08,514 -- Build files have been written to: /tmp/tmp6p3xbct_/build 2024-02-08T13:49:08,526 *** Building project with Ninja... 2024-02-08T13:49:08,873 [1/22] cd /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-02-08T13:49:08,873 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-08T13:49:08,999 [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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/build-info.cpp 2024-02-08T13:49:11,190 [3/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/ggml-alloc.c 2024-02-08T13:49:15,401 [4/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/ggml-backend.c 2024-02-08T13:49:19,228 [5/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/console.cpp 2024-02-08T13:49:21,324 [6/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/sampling.cpp 2024-02-08T13:49:27,968 [7/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/grammar-parser.cpp 2024-02-08T13:49:35,221 [8/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/llava.cpp 2024-02-08T13:49:37,602 [9/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/train.cpp 2024-02-08T13:49:47,341 [10/22] /usr/bin/c++ -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/llava-cli.cpp 2024-02-08T13:49:52,725 [11/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/ggml-quants.c 2024-02-08T13:50:07,517 [12/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/common.cpp 2024-02-08T13:50:07,517 In file included from /usr/include/c++/12/vector:70, 2024-02-08T13:50:07,519 from /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-08T13:50:07,519 from /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/sampling.h:5, 2024-02-08T13:50:07,548 from /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/common.h:7, 2024-02-08T13:50:07,549 from /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/common.cpp:1: 2024-02-08T13:50:07,555 /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]’: 2024-02-08T13:50:07,556 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-08T13:50:07,565 439 | vector<_Tp, _Alloc>:: 2024-02-08T13:50:07,566 | ^~~~~~~~~~~~~~~~~~~ 2024-02-08T13:50:07,576 /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]’: 2024-02-08T13:50:07,577 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-08T13:50:07,584 In file included from /usr/include/c++/12/vector:64: 2024-02-08T13:50:07,585 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-08T13:50:07,591 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/common.cpp:850:42: 2024-02-08T13:50:07,592 /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 2024-02-08T13:50:07,593 1287 | _M_realloc_insert(end(), __x); 2024-02-08T13:50:07,600 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-08T13:50:07,601 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-08T13:50:07,602 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/common/common.cpp:895:41: 2024-02-08T13:50:07,608 /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 2024-02-08T13:50:07,609 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-02-08T13:50:07,610 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:50:12,709 [13/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/ggml.c 2024-02-08T13:50:12,930 [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 && : 2024-02-08T13:50:13,079 [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 && : 2024-02-08T13:50:32,088 [16/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/examples/llava/clip.cpp 2024-02-08T13:50:32,429 [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 && : 2024-02-08T13:51:00,037 [18/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp 2024-02-08T13:51:00,037 In file included from /usr/include/c++/12/vector:64, 2024-02-08T13:51:00,037 from /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.h:908, 2024-02-08T13:51:00,038 from /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:2: 2024-02-08T13:51:00,039 /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]’: 2024-02-08T13:51:00,039 /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 2024-02-08T13:51:00,040 673 | vector(initializer_list __l, 2024-02-08T13:51:00,040 | ^~~~~~ 2024-02-08T13:51:00,041 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/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*)’: 2024-02-08T13:51:00,041 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3528:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,042 3528 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,042 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,043 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3532:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,043 3532 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,044 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,044 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3533:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,045 3533 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,045 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,046 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3563:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,046 3563 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,046 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,047 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3564:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,047 3564 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-08T13:51:00,047 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,048 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3565:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,048 3565 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,049 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,049 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3581:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,050 3581 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,051 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,051 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3583:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,052 3583 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,052 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,053 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3584:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,053 3584 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,054 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,054 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3596:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,055 3596 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,055 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,056 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3604:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,056 3604 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,057 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,057 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3609:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,057 3609 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,058 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,058 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3613:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,058 3613 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,059 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,060 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3614:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,060 3614 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,061 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,062 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3616:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,062 3616 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,063 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,063 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3618:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,064 3618 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-02-08T13:51:00,064 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,065 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3630:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,066 3630 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,066 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,067 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3633:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,067 3633 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-02-08T13:51:00,068 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,068 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3634:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,069 3634 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-02-08T13:51:00,069 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,070 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3637:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,070 3637 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T13:51:00,071 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,071 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3638:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,072 3638 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,072 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,073 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3641:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,073 3641 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,074 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,075 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3646:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,075 3646 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,076 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,076 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3647:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,077 3647 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-08T13:51:00,077 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,078 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3651:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,079 3651 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,079 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,080 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3652:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,080 3652 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,081 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,081 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3653:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,081 3653 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,082 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,082 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3665:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,083 3665 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T13:51:00,083 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,084 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3669:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,085 3669 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-08T13:51:00,085 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,086 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3671:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,086 3671 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,087 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,088 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3674:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,088 3674 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-08T13:51:00,089 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,089 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3683:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,090 3683 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,090 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,091 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3686:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,091 3686 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,092 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,092 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3687:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,092 3687 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,093 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,093 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3688:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,094 3688 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,095 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,095 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3698:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,096 3698 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,097 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,097 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3703:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,098 3703 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,098 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,099 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3704:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,099 3704 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-08T13:51:00,100 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,100 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3707:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,101 3707 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T13:51:00,102 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,102 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3709:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,103 3709 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,103 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,104 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3712:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,104 3712 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,104 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,105 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3715:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,105 3715 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {64}); 2024-02-08T13:51:00,106 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,106 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3716:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,107 3716 | layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias", i), {64}); 2024-02-08T13:51:00,107 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,108 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3719:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,108 3719 | layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), {64}); 2024-02-08T13:51:00,109 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,109 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3724:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,110 3724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,111 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,111 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3725:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,112 3725 | model.tok_norm = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,113 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,113 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3726:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,114 3726 | model.tok_norm_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,115 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,115 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3730:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,116 3730 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,116 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,117 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3731:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,117 3731 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,118 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,119 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3732:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,119 3732 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,120 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,120 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3741:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,121 3741 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,122 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,123 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3742:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,123 3742 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,124 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,124 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3744:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,125 3744 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T13:51:00,126 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,126 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3745:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,127 3745 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-02-08T13:51:00,128 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,128 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3748:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,129 3748 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-08T13:51:00,129 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,130 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3750:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,130 3750 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,131 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,131 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3754:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,132 3754 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T13:51:00,132 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,133 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3762:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,133 3762 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,134 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,135 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3766:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,135 3766 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,136 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,136 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3767:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,137 3767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,138 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,138 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3776:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,139 3776 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,140 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,140 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3778:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,141 3778 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-08T13:51:00,141 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,142 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3779:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,142 3779 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,143 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,143 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3786:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,143 3786 | layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false); 2024-02-08T13:51:00,144 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,145 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3791:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,146 3791 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,146 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,147 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3795:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,148 3795 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,149 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,149 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3796:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,150 3796 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,150 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,151 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3797:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,151 3797 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,152 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,153 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3806:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,154 3806 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,154 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,154 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3807:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,155 3807 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,155 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,156 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3809:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,156 3809 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,157 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,157 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3810:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,158 3810 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,159 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,160 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3816:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,160 3816 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}, false); 2024-02-08T13:51:00,161 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,162 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3820:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,163 3820 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,164 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,165 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3824:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,165 3824 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,166 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,167 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3829:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,168 3829 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,169 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,169 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3833:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,170 3833 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,170 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,171 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3834:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,171 3834 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,172 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,172 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3843:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,173 3843 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,173 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,174 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3846:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,175 3846 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd*3}); 2024-02-08T13:51:00,175 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,176 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3851:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,177 3851 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2}); 2024-02-08T13:51:00,177 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,178 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3853:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,179 3853 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff/2}); 2024-02-08T13:51:00,179 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,180 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3858:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,181 3858 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,182 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,183 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3862:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,183 3862 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,184 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,185 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3863:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,185 3863 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,186 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,186 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3872:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,187 3872 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,188 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,189 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3876:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,190 3876 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,190 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,191 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3877:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,192 3877 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,193 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,193 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3881:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,194 3881 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-08T13:51:00,194 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,195 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3882:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,196 3882 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-08T13:51:00,196 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,197 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3887:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,198 3887 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-08T13:51:00,199 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,200 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3893:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,200 3893 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,201 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,201 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3897:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,202 3897 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,202 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,203 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3898:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,204 3898 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,204 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,205 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3899:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,205 3899 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,206 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,207 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3900:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,207 3900 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-02-08T13:51:00,208 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,209 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3909:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,210 3909 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,210 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,211 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3910:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,212 3910 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,213 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,214 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3912:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,214 3912 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, false); 2024-02-08T13:51:00,215 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,216 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3916:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,216 3916 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,217 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,217 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3917:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,218 3917 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-02-08T13:51:00,219 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,219 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3919:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,220 3919 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,221 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,222 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3920:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,223 3920 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-08T13:51:00,223 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,224 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3922:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,225 3922 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,225 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,226 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3923:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,227 3923 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-08T13:51:00,227 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,228 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3926:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,229 3926 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,229 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,229 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3929:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,230 3929 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-08T13:51:00,230 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,231 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3930:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,231 3930 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T13:51:00,232 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,232 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3933:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,233 3933 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-08T13:51:00,234 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,235 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3938:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,235 3938 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,236 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,237 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3942:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,238 3942 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,238 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,239 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3943:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,240 3943 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,240 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,241 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3952:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,242 3952 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-08T13:51:00,243 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,243 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3954:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,244 3954 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,245 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,245 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3955:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,246 3955 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,246 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,247 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3959:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,248 3959 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-08T13:51:00,248 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,249 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3966:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,250 3966 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,251 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,252 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3967:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,252 3967 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-08T13:51:00,253 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,254 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3971:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,255 3971 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,256 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,257 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3972:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,259 3972 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,260 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,261 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3973:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,262 3973 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,263 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,264 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3988:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,265 3988 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,266 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,266 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:3998:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,267 3998 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-08T13:51:00,268 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,268 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4003:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,269 4003 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,270 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,271 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4007:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,272 4007 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,273 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,274 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4008:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,274 4008 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,275 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,276 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4009:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,276 4009 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,277 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,278 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4019:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,279 4019 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-08T13:51:00,280 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,280 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4024:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,281 4024 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-08T13:51:00,281 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,282 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4031:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,283 4031 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-08T13:51:00,283 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,284 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4039:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,285 4039 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,285 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,286 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4041:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,287 4041 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,289 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,290 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4042:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,291 4042 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-08T13:51:00,292 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,293 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4043:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,294 4043 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,296 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,297 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4055:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,298 4055 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-08T13:51:00,299 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,299 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4069:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,300 4069 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,300 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,300 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4073:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,301 4073 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-08T13:51:00,301 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,302 /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/vendor/llama.cpp/llama.cpp:4074:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-08T13:51:00,303 4074 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-08T13:51:00,303 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,304 In file included from /usr/include/c++/12/vector:70: 2024-02-08T13:51:00,305 /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]’: 2024-02-08T13:51:00,305 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-08T13:51:00,306 439 | vector<_Tp, _Alloc>:: 2024-02-08T13:51:00,307 | ^~~~~~~~~~~~~~~~~~~ 2024-02-08T13:51:00,307 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-08T13:51:00,308 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, 2024-02-08T13:51:00,308 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, 2024-02-08T13:51:00,309 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-08T13:51:00,310 /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 2024-02-08T13:51:00,310 1287 | _M_realloc_insert(end(), __x); 2024-02-08T13:51:00,311 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-08T13:51:00,311 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-08T13:51:00,312 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, 2024-02-08T13:51:00,313 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, 2024-02-08T13:51:00,313 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-08T13:51:00,314 /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 2024-02-08T13:51:00,314 1287 | _M_realloc_insert(end(), __x); 2024-02-08T13:51:00,315 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-08T13:51:00,450 [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 && : 2024-02-08T13:51:00,746 [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 && : 2024-02-08T13:51:00,810 [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/tmp6p3xbct_/build/vendor/llama.cpp: vendor/llama.cpp/libllama.so && : 2024-02-08T13:51:01,063 [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/tmp6p3xbct_/build/vendor/llama.cpp: vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.so && : 2024-02-08T13:51:01,067 *** Installing project into wheel... 2024-02-08T13:51:01,105 -- Install configuration: "Release" 2024-02-08T13:51:01,109 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/lib/libggml_shared.so 2024-02-08T13:51:01,158 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-02-08T13:51:01,161 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-02-08T13:51:01,165 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/include/ggml.h 2024-02-08T13:51:01,169 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/include/ggml-alloc.h 2024-02-08T13:51:01,171 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/include/ggml-backend.h 2024-02-08T13:51:01,174 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/lib/libllama.so 2024-02-08T13:51:01,244 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/include/llama.h 2024-02-08T13:51:01,249 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/bin/convert.py 2024-02-08T13:51:01,253 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/bin/convert-lora-to-ggml.py 2024-02-08T13:51:01,257 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/llama_core/libllama.so 2024-02-08T13:51:01,324 -- Installing: /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/llama_core/libllama.so 2024-02-08T13:51:01,395 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/lib/libllava.so 2024-02-08T13:51:01,415 -- Set runtime path of "/tmp/tmp6p3xbct_/wheel/platlib/lib/libllava.so" to "" 2024-02-08T13:51:01,455 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/bin/llava-cli 2024-02-08T13:51:01,471 -- Set runtime path of "/tmp/tmp6p3xbct_/wheel/platlib/bin/llava-cli" to "" 2024-02-08T13:51:01,500 -- Installing: /tmp/tmp6p3xbct_/wheel/platlib/llama_core/libllava.so 2024-02-08T13:51:01,520 -- Set runtime path of "/tmp/tmp6p3xbct_/wheel/platlib/llama_core/libllava.so" to "" 2024-02-08T13:51:01,564 -- Installing: /tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/llama_core/libllava.so 2024-02-08T13:51:01,586 -- Set runtime path of "/tmp/pip-wheel-jduvmrg5/llama-core_d8b63c1c865441619fbf433deb18ebe5/llama_core/libllava.so" to "" 2024-02-08T13:51:01,634 *** Making wheel... 2024-02-08T13:51:02,972 *** Created llama_core-0.0.2-cp311-cp311-manylinux_2_36_armv7l.whl... 2024-02-08T13:51:03,029 Building wheel for llama-core (pyproject.toml): finished with status 'done' 2024-02-08T13:51:03,058 Created wheel for llama-core: filename=llama_core-0.0.2-cp311-cp311-manylinux_2_36_armv7l.whl size=2355348 sha256=39b6da3d8b2c0a1bf4fe8ea9c6e0c25dc5ee291ba2d893e01751a684696ada6f 2024-02-08T13:51:03,059 Stored in directory: /tmp/pip-ephem-wheel-cache-hl1dh2pe/wheels/c1/ba/31/60311de152f03c477cad23e351cd72395b780ba78ba62b0c8c 2024-02-08T13:51:03,070 Successfully built llama-core 2024-02-08T13:51:03,137 Removed build tracker: '/tmp/pip-build-tracker-om9154xw'