2024-03-20T01:38:58,799 Created temporary directory: /tmp/pip-build-tracker-rfc904rr 2024-03-20T01:38:58,800 Initialized build tracking at /tmp/pip-build-tracker-rfc904rr 2024-03-20T01:38:58,801 Created build tracker: /tmp/pip-build-tracker-rfc904rr 2024-03-20T01:38:58,801 Entered build tracker: /tmp/pip-build-tracker-rfc904rr 2024-03-20T01:38:58,801 Created temporary directory: /tmp/pip-wheel-cp9wrho5 2024-03-20T01:38:58,806 Created temporary directory: /tmp/pip-ephem-wheel-cache-5g7t_75j 2024-03-20T01:38:58,829 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-03-20T01:38:58,833 2 location(s) to search for versions of llama-cpp-conv: 2024-03-20T01:38:58,833 * https://pypi.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,833 * https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,834 Fetching project page and analyzing links: https://pypi.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,834 Getting page https://pypi.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,836 Found index url https://pypi.org/simple/ 2024-03-20T01:38:58,895 Fetched page https://pypi.org/simple/llama-cpp-conv/ as application/vnd.pypi.simple.v1+json 2024-03-20T01:38:58,902 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/6a/db/4944f6684c51fcd0d35e5c921facd6b92a983e615ca817aec0b8b0c94ffc/llama_cpp_conv-0.2.57-cp310-cp310-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,902 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/d7/cc/564d25d2901080b43b0d8e1c45f1cc56885094995f8f9db86e79ee47bb41/llama_cpp_conv-0.2.57-cp310-cp310-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,902 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/8f/df/f87f4d9c40d893cdee3f63b955d78509288954db0ea4c1783e7e6ec48e53/llama_cpp_conv-0.2.57-cp310-cp310-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,902 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/66/dd/b92b89e1a7fb9231907fda5373619fad83e3e593726457163e17a148952b/llama_cpp_conv-0.2.57-cp310-cp310-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,903 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/57/25/fca00deea19ee3e3ba6a577a47fe15360e20df2e7265be579480b4c29e09/llama_cpp_conv-0.2.57-cp310-cp310-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,903 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/4a/12/013261b42bbcda7c977eae75336b082196c11369c1f69e1d1cff60047a42/llama_cpp_conv-0.2.57-cp310-cp310-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,903 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/21/51/37d5fcd3317aae2124bf575f57a2775945cef99dd606e18d3bf019e16764/llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,903 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/40/89/3059ebaf400fe630ae8fc628f2b2d4d146a5a8b328b54ac74a99e1be5430/llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,903 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/bb/33/32be068bff0fa283f0646a99b5bb1812540aa142b323dc4f3179378ca2e2/llama_cpp_conv-0.2.57-cp311-cp311-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,904 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/2e/c7/ec440f3993a45cbc579107a1f2b4f8c61e0bab36ceedef2fd962b9ef25f7/llama_cpp_conv-0.2.57-cp311-cp311-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,904 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/ec/6d/c9713de408baa2a9410ce449c5308b7c5f2b5054d3ac5b5616d10e4a3a6d/llama_cpp_conv-0.2.57-cp311-cp311-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,904 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/31/fc/06cfa6ef71dc5e8683f23b681ccfd420b17616cd85e7c39fd304a65a4f8a/llama_cpp_conv-0.2.57-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,904 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/e2/7a/f5f1d56fc866dcfe547fb92d0111a998b7d53e9fbd412d6b6bb66c631906/llama_cpp_conv-0.2.57-cp38-cp38-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,904 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/06/a7/39dd6198298d8d27a454b30a4cb18a48f4a96e064c25fae2cc4c97ff771d/llama_cpp_conv-0.2.57-cp38-cp38-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,905 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/c6/b0/d1047e56e844d6e29d6839c24aaefabf576efad74c4932ab46435f9945f7/llama_cpp_conv-0.2.57-cp38-cp38-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,905 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/23/37/7b3f4e04e3fe0408e77eb3cec6a6ecdd5200da19f49334fe7e2ef30e3f28/llama_cpp_conv-0.2.57-cp38-cp38-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,905 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/94/fb/0dad5b4f320c25cd2c90e07476db75888ebfe958f1851d8a26337ac2271b/llama_cpp_conv-0.2.57-cp38-cp38-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,905 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/a5/f2/33063bcceb39fc5fb0fa436058afcd376fc3f7ee30018346108478daeff5/llama_cpp_conv-0.2.57-cp38-cp38-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,905 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/66/6e/63286e7a0c8158e5811f8c7000f81694c2c02d2b6a54f43b05cb30fdb649/llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,905 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/84/c8/359a8b2cdae109b4563b5993d9c560c3c45948e30ad5b83c7e0d674707df/llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,906 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/4d/0a/f514431e2cb8dc56378b17c131ca2d77d61dfa2169219f51589897475c64/llama_cpp_conv-0.2.57-cp39-cp39-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,906 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/08/f9/e981e918989ee556d1ff07b3508ac8ee59c10c8c21879b27ab5b01f36a99/llama_cpp_conv-0.2.57-cp39-cp39-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,906 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/74/d8/0b80732b9c0a37a36c326a5f694ad9d5a82048502638ef700fe5bc4ff4a4/llama_cpp_conv-0.2.57-cp39-cp39-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,906 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/d2/e4/714e08ceeb70d13eee9acae81cb1a150ba8dbc2dfe0188328f474aa63336/llama_cpp_conv-0.2.57-cp39-cp39-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,906 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/04/81/db6e3d121db9394160c3ed83c0f6c115a5e54415e0cd5bd807c46cd5fec9/llama_cpp_conv-0.2.57-pp38-pypy38_pp73-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,907 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/8c/e9/2e888f7b10cbf4625f5a0c76a0db8ba0d6af355193dddc91e45d18704bde/llama_cpp_conv-0.2.57-pp38-pypy38_pp73-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,907 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/27/11/21f92fd36ae7d2d38df0691c545f51fb0d3d747df5fc31291fa700741e5d/llama_cpp_conv-0.2.57-pp38-pypy38_pp73-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,907 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/be/c8/0fdc549df836ceeea6e8a9b7a8b2454052f4c6fa2c34fb0bab648ade7ed5/llama_cpp_conv-0.2.57-pp39-pypy39_pp73-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,907 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/c9/55/c738382bb1d2d45d107a70db456f8c26022cb1e9f729d757d6578a04b88c/llama_cpp_conv-0.2.57-pp39-pypy39_pp73-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,907 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/00/4e/3a809a80510c5f3f8032954ca330b02088a0ad7225d43c69edef100bd1e9/llama_cpp_conv-0.2.57-pp39-pypy39_pp73-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,908 Found link https://files.pythonhosted.org/packages/8d/d1/2a1b6cd2046cc322f8792af985a4b53acd8c47fa238db44fd1a6f21bd1f2/llama_cpp_conv-0.2.57.tar.gz (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8), version: 0.2.57 2024-03-20T01:38:58,908 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,909 Getting page https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,910 Found index url https://www.piwheels.org/simple/ 2024-03-20T01:38:58,982 Fetched page https://www.piwheels.org/simple/llama-cpp-conv/ as text/html 2024-03-20T01:38:58,983 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=c851c1100f9c04f112ebaaa0bb42bbc9ddbc7760a84e8d13e6610cddccde1912 (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-03-20T01:38:58,983 Skipping link: not a file: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,983 Skipping link: not a file: https://pypi.org/simple/llama-cpp-conv/ 2024-03-20T01:38:58,999 Given no hashes to check 1 links for project 'llama-cpp-conv': discarding no candidates 2024-03-20T01:38:59,014 Collecting llama-cpp-conv==0.2.57 2024-03-20T01:38:59,016 Created temporary directory: /tmp/pip-unpack-c2y6mhry 2024-03-20T01:38:59,066 Downloading llama_cpp_conv-0.2.57.tar.gz (37.6 MB) 2024-03-20T01:39:04,392 Added llama-cpp-conv==0.2.57 from https://files.pythonhosted.org/packages/8d/d1/2a1b6cd2046cc322f8792af985a4b53acd8c47fa238db44fd1a6f21bd1f2/llama_cpp_conv-0.2.57.tar.gz to build tracker '/tmp/pip-build-tracker-rfc904rr' 2024-03-20T01:39:04,397 Created temporary directory: /tmp/pip-build-env-pho0hrvj 2024-03-20T01:39:04,407 Installing build dependencies: started 2024-03-20T01:39:04,408 Running command pip subprocess to install build dependencies 2024-03-20T01:39:05,564 Using pip 24.0 from /usr/local/lib/python3.9/dist-packages/pip (python 3.9) 2024-03-20T01:39:06,089 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-03-20T01:39:06,499 Collecting scikit-build-core>=0.5.1 (from scikit-build-core[pyproject]>=0.5.1) 2024-03-20T01:39:06,518 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.2-py3-none-any.whl (140 kB) 2024-03-20T01:39:06,793 Collecting exceptiongroup (from scikit-build-core>=0.5.1->scikit-build-core[pyproject]>=0.5.1) 2024-03-20T01:39:06,816 Using cached https://www.piwheels.org/simple/exceptiongroup/exceptiongroup-1.2.0-py3-none-any.whl (16 kB) 2024-03-20T01:39:06,994 Collecting packaging>=20.9 (from scikit-build-core>=0.5.1->scikit-build-core[pyproject]>=0.5.1) 2024-03-20T01:39:07,010 Using cached https://www.piwheels.org/simple/packaging/packaging-24.0-py3-none-any.whl (53 kB) 2024-03-20T01:39:07,142 Collecting tomli>=1.1 (from scikit-build-core>=0.5.1->scikit-build-core[pyproject]>=0.5.1) 2024-03-20T01:39:07,158 Using cached https://www.piwheels.org/simple/tomli/tomli-2.0.1-py3-none-any.whl (12 kB) 2024-03-20T01:39:07,279 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]>=0.5.1) 2024-03-20T01:39:07,296 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-03-20T01:39:07,380 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]>=0.5.1) 2024-03-20T01:39:07,411 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-03-20T01:39:09,123 Installing collected packages: tomli, pathspec, packaging, exceptiongroup, scikit-build-core, pyproject-metadata 2024-03-20T01:39:09,908 Successfully installed exceptiongroup-1.2.0 packaging-24.0 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.2 tomli-2.0.1 2024-03-20T01:39:10,325 Installing build dependencies: finished with status 'done' 2024-03-20T01:39:10,330 Getting requirements to build wheel: started 2024-03-20T01:39:10,331 Running command Getting requirements to build wheel 2024-03-20T01:39:10,780 Getting requirements to build wheel: finished with status 'done' 2024-03-20T01:39:10,797 Installing backend dependencies: started 2024-03-20T01:39:10,798 Running command pip subprocess to install backend dependencies 2024-03-20T01:39:11,946 Using pip 24.0 from /usr/local/lib/python3.9/dist-packages/pip (python 3.9) 2024-03-20T01:39:12,473 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-03-20T01:39:13,531 Collecting cmake>=3.21 2024-03-20T01:39:13,550 Using cached https://www.piwheels.org/simple/cmake/cmake-3.28.3-cp39-cp39-linux_armv7l.whl (19.6 MB) 2024-03-20T01:39:15,715 Installing collected packages: cmake 2024-03-20T01:39:21,823 Creating /tmp/pip-build-env-pho0hrvj/normal/bin 2024-03-20T01:39:21,825 changing mode of /tmp/pip-build-env-pho0hrvj/normal/bin/cmake to 755 2024-03-20T01:39:21,827 changing mode of /tmp/pip-build-env-pho0hrvj/normal/bin/cpack to 755 2024-03-20T01:39:21,829 changing mode of /tmp/pip-build-env-pho0hrvj/normal/bin/ctest to 755 2024-03-20T01:39:21,909 Successfully installed cmake-3.28.3 2024-03-20T01:39:22,357 Installing backend dependencies: finished with status 'done' 2024-03-20T01:39:22,359 Created temporary directory: /tmp/pip-modern-metadata-251kjt1o 2024-03-20T01:39:22,362 Preparing metadata (pyproject.toml): started 2024-03-20T01:39:22,363 Running command Preparing metadata (pyproject.toml) 2024-03-20T01:39:22,882 *** scikit-build-core 0.8.2 using CMake 3.28.3 (metadata_wheel) 2024-03-20T01:39:22,979 Preparing metadata (pyproject.toml): finished with status 'done' 2024-03-20T01:39:22,988 Source in /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56 has version 0.2.57, which satisfies requirement llama-cpp-conv==0.2.57 from https://files.pythonhosted.org/packages/8d/d1/2a1b6cd2046cc322f8792af985a4b53acd8c47fa238db44fd1a6f21bd1f2/llama_cpp_conv-0.2.57.tar.gz 2024-03-20T01:39:22,988 Removed llama-cpp-conv==0.2.57 from https://files.pythonhosted.org/packages/8d/d1/2a1b6cd2046cc322f8792af985a4b53acd8c47fa238db44fd1a6f21bd1f2/llama_cpp_conv-0.2.57.tar.gz from build tracker '/tmp/pip-build-tracker-rfc904rr' 2024-03-20T01:39:22,998 Created temporary directory: /tmp/pip-unpack-50u8msvn 2024-03-20T01:39:22,999 Created temporary directory: /tmp/pip-unpack-r7nalunk 2024-03-20T01:39:23,062 Building wheels for collected packages: llama-cpp-conv 2024-03-20T01:39:23,066 Created temporary directory: /tmp/pip-wheel-wd9lf1st 2024-03-20T01:39:23,067 Destination directory: /tmp/pip-wheel-wd9lf1st 2024-03-20T01:39:23,069 Building wheel for llama-cpp-conv (pyproject.toml): started 2024-03-20T01:39:23,070 Running command Building wheel for llama-cpp-conv (pyproject.toml) 2024-03-20T01:39:23,559 *** scikit-build-core 0.8.2 using CMake 3.28.3 (wheel) 2024-03-20T01:39:23,579 *** Configuring CMake... 2024-03-20T01:39:23,646 loading initial cache file /tmp/tmpnbxj_hga/build/CMakeInit.txt 2024-03-20T01:39:23,898 -- The C compiler identification is GNU 10.2.1 2024-03-20T01:39:24,195 -- The CXX compiler identification is GNU 10.2.1 2024-03-20T01:39:24,267 -- Detecting C compiler ABI info 2024-03-20T01:39:24,566 -- Detecting C compiler ABI info - done 2024-03-20T01:39:24,603 -- Check for working C compiler: /usr/bin/cc - skipped 2024-03-20T01:39:24,605 -- Detecting C compile features 2024-03-20T01:39:24,607 -- Detecting C compile features - done 2024-03-20T01:39:24,652 -- Detecting CXX compiler ABI info 2024-03-20T01:39:24,970 -- Detecting CXX compiler ABI info - done 2024-03-20T01:39:25,008 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-03-20T01:39:25,009 -- Detecting CXX compile features 2024-03-20T01:39:25,012 -- Detecting CXX compile features - done 2024-03-20T01:39:25,042 -- Found Git: /usr/bin/git (found version "2.30.2") 2024-03-20T01:39:25,098 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-03-20T01:39:25,370 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Failed 2024-03-20T01:39:25,370 -- Check if compiler accepts -pthread 2024-03-20T01:39:25,640 -- Check if compiler accepts -pthread - yes 2024-03-20T01:39:25,644 -- Found Threads: TRUE 2024-03-20T01:39:25,652 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-03-20T01:39:25,742 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-03-20T01:39:25,742 -- ARM detected 2024-03-20T01:39:25,746 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-03-20T01:39:26,075 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-03-20T01:39:26,114 CMake Warning (dev) at CMakeLists.txt:23 (install): 2024-03-20T01:39:26,114 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-03-20T01:39:26,114 This warning is for project developers. Use -Wno-dev to suppress it. 2024-03-20T01:39:26,115 CMake Warning (dev) at CMakeLists.txt:32 (install): 2024-03-20T01:39:26,115 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-03-20T01:39:26,115 This warning is for project developers. Use -Wno-dev to suppress it. 2024-03-20T01:39:26,116 -- Configuring done (2.5s) 2024-03-20T01:39:26,179 -- Generating done (0.0s) 2024-03-20T01:39:26,196 -- Build files have been written to: /tmp/tmpnbxj_hga/build 2024-03-20T01:39:26,206 *** Building project with Ninja... 2024-03-20T01:39:26,223 Change Dir: '/tmp/tmpnbxj_hga/build' 2024-03-20T01:39:26,224 Run Build Command(s): /usr/bin/ninja -v 2024-03-20T01:39:28,719 [1/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/ggml-alloc.c 2024-03-20T01:39:28,986 [2/20] cd /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp && /tmp/pip-build-env-pho0hrvj/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -DMSVC= -DCMAKE_C_COMPILER_VERSION=10.2.1 -DCMAKE_C_COMPILER_ID=GNU -DCMAKE_VS_PLATFORM_NAME= -DCMAKE_C_COMPILER=/usr/bin/cc -P /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-03-20T01:39:28,986 -- Found Git: /usr/bin/git (found version "2.30.2") 2024-03-20T01:39:29,216 [3/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/build-info.cpp 2024-03-20T01:39:31,307 [4/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/ggml-backend.c 2024-03-20T01:39:39,622 [5/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/. -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/sampling.cpp 2024-03-20T01:39:39,769 [6/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/unicode.cpp 2024-03-20T01:39:42,822 [7/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/. -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/console.cpp 2024-03-20T01:39:48,988 [8/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/. -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/grammar-parser.cpp 2024-03-20T01:39:57,981 [9/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/. -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/train.cpp 2024-03-20T01:40:01,339 [10/20] /usr/bin/c++ -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/examples/quantize/../../common -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -MF vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o.d -o vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/examples/quantize/quantize.cpp 2024-03-20T01:40:09,499 [11/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/ggml-quants.c 2024-03-20T01:40:10,406 [12/20] /usr/bin/c++ -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/. -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o -MF vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o.d -o vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/examples/imatrix/imatrix.cpp 2024-03-20T01:40:15,243 [13/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/. -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.cpp 2024-03-20T01:40:15,243 In file included from /usr/include/c++/10/vector:72, 2024-03-20T01:40:15,243 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/grammar-parser.h:14, 2024-03-20T01:40:15,243 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/sampling.h:5, 2024-03-20T01:40:15,244 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.h:7, 2024-03-20T01:40:15,244 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.cpp:1: 2024-03-20T01:40:15,244 /usr/include/c++/10/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(std::vector<_Tp, _Alloc>::iterator, _Args&& ...) [with _Args = {const llama_model_kv_override&}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-03-20T01:40:15,244 /usr/include/c++/10/bits/vector.tcc:426:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-03-20T01:40:15,244 426 | vector<_Tp, _Alloc>:: 2024-03-20T01:40:15,245 | ^~~~~~~~~~~~~~~~~~~ 2024-03-20T01:40:15,245 /usr/include/c++/10/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(std::vector<_Tp, _Alloc>::iterator, _Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-03-20T01:40:15,245 /usr/include/c++/10/bits/vector.tcc:426:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-03-20T01:40:15,245 In file included from /usr/include/c++/10/vector:67, 2024-03-20T01:40:15,245 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/grammar-parser.h:14, 2024-03-20T01:40:15,246 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/sampling.h:5, 2024-03-20T01:40:15,246 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.h:7, 2024-03-20T01:40:15,246 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.cpp:1: 2024-03-20T01:40:15,246 /usr/include/c++/10/bits/stl_vector.h: In function ‘bool gpt_params_find_arg(int, char**, gpt_params&, int&, bool&)’: 2024-03-20T01:40:15,246 /usr/include/c++/10/bits/stl_vector.h:1198:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-03-20T01:40:15,247 1198 | _M_realloc_insert(end(), __x); 2024-03-20T01:40:15,247 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-03-20T01:40:15,247 In file included from /usr/include/c++/10/vector:72, 2024-03-20T01:40:15,247 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/grammar-parser.h:14, 2024-03-20T01:40:15,247 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/sampling.h:5, 2024-03-20T01:40:15,248 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.h:7, 2024-03-20T01:40:15,248 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/common/common.cpp:1: 2024-03-20T01:40:15,248 /usr/include/c++/10/bits/vector.tcc: In function ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’: 2024-03-20T01:40:15,248 /usr/include/c++/10/bits/vector.tcc:121:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-03-20T01:40:15,249 121 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-03-20T01:40:15,249 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-20T01:40:24,640 [14/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu11 -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/ggml.c 2024-03-20T01:40:24,729 [15/20] : && /tmp/pip-build-env-pho0hrvj/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/libggml_static.a && /usr/bin/ar qc vendor/llama.cpp/libggml_static.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && : 2024-03-20T01:41:15,666 [16/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/. -O3 -DNDEBUG -std=gnu++11 -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -pthread -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp 2024-03-20T01:41:15,666 In file included from /usr/include/c++/10/vector:67, 2024-03-20T01:41:15,667 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.h:985, 2024-03-20T01:41:15,667 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:2: 2024-03-20T01:41:15,667 /usr/include/c++/10/bits/stl_vector.h: In function ‘std::vector<_Tp, _Alloc>::vector(std::initializer_list<_Tp>, const allocator_type&) [with _Tp = long long int; _Alloc = std::allocator]’: 2024-03-20T01:41:15,667 /usr/include/c++/10/bits/stl_vector.h:625:7: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,667 625 | vector(initializer_list __l, 2024-03-20T01:41:15,667 | ^~~~~~ 2024-03-20T01:41:15,667 /usr/include/c++/10/bits/stl_vector.h: In function ‘std::vector<_Tp, _Alloc>::vector(std::initializer_list<_Tp>, const allocator_type&) [with _Tp = long long int; _Alloc = std::allocator]’: 2024-03-20T01:41:15,667 /usr/include/c++/10/bits/stl_vector.h:625:7: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,668 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/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*)’: 2024-03-20T01:41:15,668 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4209:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,668 4209 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,668 | ^ 2024-03-20T01:41:15,668 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4213:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,668 4213 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,668 | ^ 2024-03-20T01:41:15,668 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4215:136: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,668 4215 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-20T01:41:15,669 | ^ 2024-03-20T01:41:15,669 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4218:131: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,669 4218 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,669 | ^ 2024-03-20T01:41:15,669 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4252:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,669 4252 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-03-20T01:41:15,669 | ^ 2024-03-20T01:41:15,669 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4253:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,670 4253 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-03-20T01:41:15,670 | ^ 2024-03-20T01:41:15,670 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4254:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,670 4254 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-20T01:41:15,670 | ^ 2024-03-20T01:41:15,670 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4270:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,670 4270 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,670 | ^ 2024-03-20T01:41:15,670 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4272:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,671 4272 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,671 | ^ 2024-03-20T01:41:15,671 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4273:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,671 4273 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,671 | ^ 2024-03-20T01:41:15,671 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4298:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,671 4298 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,671 | ^ 2024-03-20T01:41:15,672 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4302:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,672 4302 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,672 | ^ 2024-03-20T01:41:15,672 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4303:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,672 4303 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,672 | ^ 2024-03-20T01:41:15,673 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4305:144: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,673 4305 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-20T01:41:15,673 | ^ 2024-03-20T01:41:15,673 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4307:133: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,674 4307 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-03-20T01:41:15,674 | ^ 2024-03-20T01:41:15,674 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4323:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,674 4323 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-03-20T01:41:15,674 | ^ 2024-03-20T01:41:15,674 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4324:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,675 4324 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-03-20T01:41:15,675 | ^ 2024-03-20T01:41:15,675 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4336:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,675 4336 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,675 | ^ 2024-03-20T01:41:15,675 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4337:132: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,675 4337 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-03-20T01:41:15,676 | ^ 2024-03-20T01:41:15,676 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4341:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,676 4341 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,676 | ^ 2024-03-20T01:41:15,676 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4342:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,676 4342 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,677 | ^ 2024-03-20T01:41:15,677 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4343:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,677 4343 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,677 | ^ 2024-03-20T01:41:15,677 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4373:121: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,677 4373 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,678 | ^ 2024-03-20T01:41:15,678 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4376:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,678 4376 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,678 | ^ 2024-03-20T01:41:15,678 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4377:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,678 4377 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,679 | ^ 2024-03-20T01:41:15,679 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4378:138: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,679 4378 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,679 | ^ 2024-03-20T01:41:15,679 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4415:125: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,679 4415 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,679 | ^ 2024-03-20T01:41:15,680 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4416:130: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,680 4416 | model.type_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_vocab_type}); 2024-03-20T01:41:15,680 | ^ 2024-03-20T01:41:15,680 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4418:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,680 4418 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-03-20T01:41:15,680 | ^ 2024-03-20T01:41:15,680 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4421:119: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,680 4421 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,681 | ^ 2024-03-20T01:41:15,681 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4422:119: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,681 4422 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,681 | ^ 2024-03-20T01:41:15,681 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4431:124: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,681 4431 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-20T01:41:15,681 | ^ 2024-03-20T01:41:15,682 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4432:116: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,682 4432 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-03-20T01:41:15,682 | ^ 2024-03-20T01:41:15,682 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4434:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,682 4434 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-03-20T01:41:15,682 | ^ 2024-03-20T01:41:15,682 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4435:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,682 4435 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-03-20T01:41:15,683 | ^ 2024-03-20T01:41:15,683 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4437:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,683 4437 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-20T01:41:15,683 | ^ 2024-03-20T01:41:15,683 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4438:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,683 4438 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-03-20T01:41:15,683 | ^ 2024-03-20T01:41:15,683 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4440:139: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,684 4440 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-03-20T01:41:15,684 | ^ 2024-03-20T01:41:15,684 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4452:122: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,684 4452 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-03-20T01:41:15,684 | ^ 2024-03-20T01:41:15,684 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4453:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,684 4453 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-03-20T01:41:15,685 | ^ 2024-03-20T01:41:15,685 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4455:122: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,685 4455 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-03-20T01:41:15,685 | ^ 2024-03-20T01:41:15,685 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4457:130: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,685 4457 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-03-20T01:41:15,686 | ^ 2024-03-20T01:41:15,686 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4466:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,686 4466 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,686 | ^ 2024-03-20T01:41:15,686 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4467:119: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,686 4467 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,686 | ^ 2024-03-20T01:41:15,687 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4468:119: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,687 4468 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,687 | ^ 2024-03-20T01:41:15,687 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4472:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,687 4472 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,687 | ^ 2024-03-20T01:41:15,688 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4473:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,688 4473 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,688 | ^ 2024-03-20T01:41:15,688 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4474:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,688 4474 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,688 | ^ 2024-03-20T01:41:15,688 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4504:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,688 4504 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,689 | ^ 2024-03-20T01:41:15,689 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4508:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,689 4508 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,689 | ^ 2024-03-20T01:41:15,689 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4509:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,689 4509 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, false); 2024-03-20T01:41:15,690 | ^ 2024-03-20T01:41:15,690 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4511:144: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,690 4511 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-20T01:41:15,690 | ^ 2024-03-20T01:41:15,690 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4513:133: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,690 4513 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-03-20T01:41:15,691 | ^ 2024-03-20T01:41:15,691 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4549:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,691 4549 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,691 | ^ 2024-03-20T01:41:15,691 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4553:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,692 4553 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,692 | ^ 2024-03-20T01:41:15,692 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4554:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,692 4554 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,692 | ^ 2024-03-20T01:41:15,692 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4555:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,693 4555 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,693 | ^ 2024-03-20T01:41:15,693 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4587:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,693 4587 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,693 | ^ 2024-03-20T01:41:15,693 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4591:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,694 4591 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,694 | ^ 2024-03-20T01:41:15,694 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4592:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,694 4592 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,694 | ^ 2024-03-20T01:41:15,695 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4616:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,695 4616 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,695 | ^ 2024-03-20T01:41:15,695 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4620:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,695 4620 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,695 | ^ 2024-03-20T01:41:15,696 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4621:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,696 4621 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,696 | ^ 2024-03-20T01:41:15,696 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4651:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,696 4651 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,696 | ^ 2024-03-20T01:41:15,697 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4655:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,697 4655 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,697 | ^ 2024-03-20T01:41:15,697 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4656:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,697 4656 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,697 | ^ 2024-03-20T01:41:15,698 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4657:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,698 4657 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,698 | ^ 2024-03-20T01:41:15,698 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4658:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,698 4658 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-03-20T01:41:15,698 | ^ 2024-03-20T01:41:15,699 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4674:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,699 4674 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-20T01:41:15,699 | ^ 2024-03-20T01:41:15,699 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4675:112: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,699 4675 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-03-20T01:41:15,699 | ^ 2024-03-20T01:41:15,700 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4677:124: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,700 4677 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-03-20T01:41:15,700 | ^ 2024-03-20T01:41:15,700 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4678:116: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,700 4678 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-03-20T01:41:15,700 | ^ 2024-03-20T01:41:15,700 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4680:124: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,700 4680 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-20T01:41:15,701 | ^ 2024-03-20T01:41:15,701 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4681:116: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,701 4681 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-03-20T01:41:15,701 | ^ 2024-03-20T01:41:15,701 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4696:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,701 4696 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,702 | ^ 2024-03-20T01:41:15,702 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4700:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,702 4700 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,702 | ^ 2024-03-20T01:41:15,702 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4701:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,702 4701 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,702 | ^ 2024-03-20T01:41:15,703 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4724:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,703 4724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,703 | ^ 2024-03-20T01:41:15,703 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4725:134: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,703 4725 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-03-20T01:41:15,703 | ^ 2024-03-20T01:41:15,704 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4729:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,704 4729 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,704 | ^ 2024-03-20T01:41:15,704 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4730:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,704 4730 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,705 | ^ 2024-03-20T01:41:15,705 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4731:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,705 4731 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,705 | ^ 2024-03-20T01:41:15,705 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4761:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,705 4761 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,705 | ^ 2024-03-20T01:41:15,705 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4765:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,706 4765 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,706 | ^ 2024-03-20T01:41:15,706 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4766:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,706 4766 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,706 | ^ 2024-03-20T01:41:15,706 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4767:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,706 4767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,707 | ^ 2024-03-20T01:41:15,707 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4797:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,707 4797 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,707 | ^ 2024-03-20T01:41:15,707 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4799:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,707 4799 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,707 | ^ 2024-03-20T01:41:15,707 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4800:128: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,707 4800 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,708 | ^ 2024-03-20T01:41:15,708 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4801:137: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,708 4801 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,708 | ^ 2024-03-20T01:41:15,708 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4827:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,708 4827 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,708 | ^ 2024-03-20T01:41:15,709 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4831:126: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,709 4831 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,709 | ^ 2024-03-20T01:41:15,709 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4832:135: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,709 4832 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,709 | ^ 2024-03-20T01:41:15,710 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4856:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,710 4856 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,710 | ^ 2024-03-20T01:41:15,710 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4859:116: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,710 4859 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,710 | ^ 2024-03-20T01:41:15,710 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4860:125: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,710 4860 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // same as tok_embd, duplicated to allow offloading 2024-03-20T01:41:15,711 | ^ 2024-03-20T01:41:15,711 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4890:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,711 4890 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,711 | ^ 2024-03-20T01:41:15,711 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4894:122: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,711 4894 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,712 | ^ 2024-03-20T01:41:15,712 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4895:122: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,712 4895 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-20T01:41:15,712 | ^ 2024-03-20T01:41:15,712 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4897:132: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,712 4897 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-20T01:41:15,712 | ^ 2024-03-20T01:41:15,712 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4900:127: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,713 4900 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,713 | ^ 2024-03-20T01:41:15,713 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4947:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,713 4947 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,713 | ^ 2024-03-20T01:41:15,713 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4951:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,713 4951 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,713 | ^ 2024-03-20T01:41:15,713 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4953:132: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,714 4953 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-20T01:41:15,714 | ^ 2024-03-20T01:41:15,714 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4956:133: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,714 4956 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,714 | ^ 2024-03-20T01:41:15,714 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4969:118: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,714 4969 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-20T01:41:15,714 | ^ 2024-03-20T01:41:15,715 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4971:123: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,715 4971 | layer.ssm_in = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, 2*d_inner}); 2024-03-20T01:41:15,715 | ^ 2024-03-20T01:41:15,715 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4973:129: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,715 4973 | layer.ssm_conv1d = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner}); 2024-03-20T01:41:15,715 | ^ 2024-03-20T01:41:15,715 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4974:121: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,715 4974 | layer.ssm_conv1d_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner}); 2024-03-20T01:41:15,716 | ^ 2024-03-20T01:41:15,716 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4976:132: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,716 4976 | layer.ssm_x = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_X, "weight", i), {d_inner, dt_rank + 2*d_state}); 2024-03-20T01:41:15,716 | ^ 2024-03-20T01:41:15,716 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4978:122: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,716 4978 | layer.ssm_dt = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_DT, "weight", i), {dt_rank, d_inner}); 2024-03-20T01:41:15,716 | ^ 2024-03-20T01:41:15,716 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4979:113: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,716 4979 | layer.ssm_dt_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_DT, "bias", i), {d_inner}); 2024-03-20T01:41:15,717 | ^ 2024-03-20T01:41:15,717 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4982:110: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,717 4982 | layer.ssm_a = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_A, i), {d_state, d_inner}); 2024-03-20T01:41:15,717 | ^ 2024-03-20T01:41:15,722 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4983:101: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,722 4983 | layer.ssm_d = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_D, i), {d_inner}); 2024-03-20T01:41:15,723 | ^ 2024-03-20T01:41:15,723 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4986:123: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,723 4986 | layer.ssm_out = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}); 2024-03-20T01:41:15,724 | ^ 2024-03-20T01:41:15,724 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4991:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,724 4991 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,724 | ^ 2024-03-20T01:41:15,724 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4995:120: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,725 4995 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-20T01:41:15,725 | ^ 2024-03-20T01:41:15,725 /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:4997:123: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-20T01:41:15,725 4997 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-20T01:41:15,725 | ^ 2024-03-20T01:41:15,726 In file included from /usr/include/c++/10/vector:72, 2024-03-20T01:41:15,726 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.h:985, 2024-03-20T01:41:15,726 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:2: 2024-03-20T01:41:15,726 /usr/include/c++/10/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(std::vector<_Tp, _Alloc>::iterator, _Args&& ...) [with _Args = {const double&}; _Tp = double; _Alloc = std::allocator]’: 2024-03-20T01:41:15,726 /usr/include/c++/10/bits/vector.tcc:426:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-03-20T01:41:15,727 426 | vector<_Tp, _Alloc>:: 2024-03-20T01:41:15,727 | ^~~~~~~~~~~~~~~~~~~ 2024-03-20T01:41:15,727 In file included from /usr/include/c++/10/vector:67, 2024-03-20T01:41:15,727 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.h:985, 2024-03-20T01:41:15,727 from /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/vendor/llama.cpp/llama.cpp:2: 2024-03-20T01:41:15,727 /usr/include/c++/10/bits/stl_vector.h: In member function ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’: 2024-03-20T01:41:15,728 /usr/include/c++/10/bits/stl_vector.h:1198:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-03-20T01:41:15,728 1198 | _M_realloc_insert(end(), __x); 2024-03-20T01:41:15,728 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-03-20T01:41:15,728 /usr/include/c++/10/bits/stl_vector.h:1198:21: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-03-20T01:41:15,728 1198 | _M_realloc_insert(end(), __x); 2024-03-20T01:41:15,729 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-03-20T01:41:15,820 [17/20] : && /tmp/pip-build-env-pho0hrvj/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/libllama.a && /usr/bin/ar qc vendor/llama.cpp/libllama.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 vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o && /usr/bin/ranlib vendor/llama.cpp/libllama.a && : 2024-03-20T01:41:15,923 [18/20] : && /tmp/pip-build-env-pho0hrvj/normal/lib/python3.9/site-packages/cmake/data/bin/cmake -E rm -f vendor/llama.cpp/common/libcommon.a && /usr/bin/ar qc vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o && /usr/bin/ranlib vendor/llama.cpp/common/libcommon.a && : 2024-03-20T01:41:16,304 [19/20] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -o vendor/llama.cpp/examples/quantize/quantize vendor/llama.cpp/libllama.a -pthread && : 2024-03-20T01:41:16,442 [20/20] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o -o vendor/llama.cpp/examples/imatrix/imatrix vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.a -pthread && : 2024-03-20T01:41:16,448 *** Installing project into wheel... 2024-03-20T01:41:16,463 -- Install configuration: "Release" 2024-03-20T01:41:16,467 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-03-20T01:41:16,470 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-03-20T01:41:16,474 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/include/ggml.h 2024-03-20T01:41:16,478 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/include/ggml-alloc.h 2024-03-20T01:41:16,480 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/include/ggml-backend.h 2024-03-20T01:41:16,483 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/lib/libllama.a 2024-03-20T01:41:16,519 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/include/llama.h 2024-03-20T01:41:16,523 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/bin/convert.py 2024-03-20T01:41:16,528 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/bin/convert-lora-to-ggml.py 2024-03-20T01:41:16,532 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/bin/quantize 2024-03-20T01:41:16,595 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/bin/imatrix 2024-03-20T01:41:16,659 -- Installing: /tmp/tmpnbxj_hga/wheel/platlib/llama_cpp/libllama.a 2024-03-20T01:41:16,686 -- Installing: /tmp/pip-wheel-cp9wrho5/llama-cpp-conv_bddca9b5144644bf96268b043c932a56/llama_cpp/libllama.a 2024-03-20T01:41:16,720 *** Making wheel... 2024-03-20T01:41:18,323 *** Created llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_31_armv7l.whl... 2024-03-20T01:41:18,380 Building wheel for llama-cpp-conv (pyproject.toml): finished with status 'done' 2024-03-20T01:41:18,411 Created wheel for llama-cpp-conv: filename=llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_31_armv7l.whl size=2582490 sha256=629119e6c3564b3c74f1a93dc42f951cf05dd112febfc51e364a791151e75eee 2024-03-20T01:41:18,412 Stored in directory: /tmp/pip-ephem-wheel-cache-5g7t_75j/wheels/56/28/6f/f2185c7b5a5b4996e281542cebbb96e952110efbef351c72ce 2024-03-20T01:41:18,428 Successfully built llama-cpp-conv 2024-03-20T01:41:18,496 Removed build tracker: '/tmp/pip-build-tracker-rfc904rr'