2024-03-19T23:42:20,454 Created temporary directory: /tmp/pip-build-tracker-wmlj8lhl 2024-03-19T23:42:20,455 Initialized build tracking at /tmp/pip-build-tracker-wmlj8lhl 2024-03-19T23:42:20,456 Created build tracker: /tmp/pip-build-tracker-wmlj8lhl 2024-03-19T23:42:20,456 Entered build tracker: /tmp/pip-build-tracker-wmlj8lhl 2024-03-19T23:42:20,457 Created temporary directory: /tmp/pip-wheel-tcrba1f1 2024-03-19T23:42:20,461 Created temporary directory: /tmp/pip-ephem-wheel-cache-reyp3ghl 2024-03-19T23:42:20,483 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-03-19T23:42:20,486 2 location(s) to search for versions of llama-cpp-conv: 2024-03-19T23:42:20,486 * https://pypi.org/simple/llama-cpp-conv/ 2024-03-19T23:42:20,486 * https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-19T23:42:20,487 Fetching project page and analyzing links: https://pypi.org/simple/llama-cpp-conv/ 2024-03-19T23:42:20,488 Getting page https://pypi.org/simple/llama-cpp-conv/ 2024-03-19T23:42:20,489 Found index url https://pypi.org/simple/ 2024-03-19T23:42:20,712 Fetched page https://pypi.org/simple/llama-cpp-conv/ as application/vnd.pypi.simple.v1+json 2024-03-19T23:42:20,719 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) 2024-03-19T23:42:20,720 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) 2024-03-19T23:42:20,720 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) 2024-03-19T23:42:20,721 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) 2024-03-19T23:42:20,721 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) 2024-03-19T23:42:20,722 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) 2024-03-19T23:42:20,723 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) 2024-03-19T23:42:20,724 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) 2024-03-19T23:42:20,724 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) 2024-03-19T23:42:20,725 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) 2024-03-19T23:42:20,725 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) 2024-03-19T23:42:20,726 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) 2024-03-19T23:42:20,727 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) 2024-03-19T23:42:20,727 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) 2024-03-19T23:42:20,728 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) 2024-03-19T23:42:20,728 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) 2024-03-19T23:42:20,729 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) 2024-03-19T23:42:20,729 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) 2024-03-19T23:42:20,730 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) 2024-03-19T23:42:20,731 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) 2024-03-19T23:42:20,731 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) 2024-03-19T23:42:20,732 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) 2024-03-19T23:42:20,732 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) 2024-03-19T23:42:20,733 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) 2024-03-19T23:42:20,734 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) 2024-03-19T23:42:20,734 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) 2024-03-19T23:42:20,735 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) 2024-03-19T23:42:20,735 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) 2024-03-19T23:42:20,736 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) 2024-03-19T23:42:20,736 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) 2024-03-19T23:42:20,737 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 2024-03-19T23:42:20,738 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-19T23:42:20,739 Getting page https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-19T23:42:20,740 Found index url https://www.piwheels.org/simple/ 2024-03-19T23:42:21,161 Fetched page https://www.piwheels.org/simple/llama-cpp-conv/ as text/html 2024-03-19T23:42:21,163 Skipping link: not a file: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-03-19T23:42:21,164 Skipping link: not a file: https://pypi.org/simple/llama-cpp-conv/ 2024-03-19T23:42:21,190 Given no hashes to check 1 links for project 'llama-cpp-conv': discarding no candidates 2024-03-19T23:42:21,219 Collecting llama-cpp-conv==0.2.57 2024-03-19T23:42:21,222 Created temporary directory: /tmp/pip-unpack-bkdmubnc 2024-03-19T23:42:21,472 Downloading llama_cpp_conv-0.2.57.tar.gz (37.6 MB) 2024-03-19T23:42:32,573 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-wmlj8lhl' 2024-03-19T23:42:32,578 Created temporary directory: /tmp/pip-build-env-vz1y10wk 2024-03-19T23:42:32,583 Installing build dependencies: started 2024-03-19T23:42:32,584 Running command pip subprocess to install build dependencies 2024-03-19T23:42:33,742 Using pip 24.0 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11) 2024-03-19T23:42:34,238 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-03-19T23:42:35,208 Collecting scikit-build-core>=0.5.1 (from scikit-build-core[pyproject]>=0.5.1) 2024-03-19T23:42:35,270 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.2-py3-none-any.whl (140 kB) 2024-03-19T23:42:35,489 WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))': /simple/packaging/ 2024-03-19T23:42:35,839 Collecting packaging>=20.9 (from scikit-build-core>=0.5.1->scikit-build-core[pyproject]>=0.5.1) 2024-03-19T23:42:35,896 Using cached https://www.piwheels.org/simple/packaging/packaging-24.0-py3-none-any.whl (53 kB) 2024-03-19T23:42:36,186 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]>=0.5.1) 2024-03-19T23:42:36,657 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-03-19T23:42:36,962 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]>=0.5.1) 2024-03-19T23:42:37,002 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-03-19T23:42:39,509 Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata 2024-03-19T23:42:40,221 Successfully installed packaging-24.0 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.2 2024-03-19T23:42:40,671 Installing build dependencies: finished with status 'done' 2024-03-19T23:42:40,674 Getting requirements to build wheel: started 2024-03-19T23:42:40,675 Running command Getting requirements to build wheel 2024-03-19T23:42:41,110 Getting requirements to build wheel: finished with status 'done' 2024-03-19T23:42:41,141 Created temporary directory: /tmp/pip-modern-metadata-ga94i1yj 2024-03-19T23:42:41,143 Preparing metadata (pyproject.toml): started 2024-03-19T23:42:41,144 Running command Preparing metadata (pyproject.toml) 2024-03-19T23:42:41,645 *** scikit-build-core 0.8.2 using CMake 3.25.1 (metadata_wheel) 2024-03-19T23:42:41,740 Preparing metadata (pyproject.toml): finished with status 'done' 2024-03-19T23:42:41,746 Source in /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89 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 2024-03-19T23:42:41,747 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-wmlj8lhl' 2024-03-19T23:42:41,756 Created temporary directory: /tmp/pip-unpack-rzjmvm9v 2024-03-19T23:42:41,757 Created temporary directory: /tmp/pip-unpack-bgj2fgjd 2024-03-19T23:42:41,815 Building wheels for collected packages: llama-cpp-conv 2024-03-19T23:42:41,819 Created temporary directory: /tmp/pip-wheel-m26pfuz2 2024-03-19T23:42:41,820 Destination directory: /tmp/pip-wheel-m26pfuz2 2024-03-19T23:42:41,822 Building wheel for llama-cpp-conv (pyproject.toml): started 2024-03-19T23:42:41,823 Running command Building wheel for llama-cpp-conv (pyproject.toml) 2024-03-19T23:42:42,315 *** scikit-build-core 0.8.2 using CMake 3.25.1 (wheel) 2024-03-19T23:42:42,335 *** Configuring CMake... 2024-03-19T23:42:42,425 loading initial cache file /tmp/tmpcjtatoia/build/CMakeInit.txt 2024-03-19T23:42:42,694 -- The C compiler identification is GNU 12.2.0 2024-03-19T23:42:42,995 -- The CXX compiler identification is GNU 12.2.0 2024-03-19T23:42:43,044 -- Detecting C compiler ABI info 2024-03-19T23:42:43,313 -- Detecting C compiler ABI info - done 2024-03-19T23:42:43,369 -- Check for working C compiler: /usr/bin/cc - skipped 2024-03-19T23:42:43,370 -- Detecting C compile features 2024-03-19T23:42:43,373 -- Detecting C compile features - done 2024-03-19T23:42:43,391 -- Detecting CXX compiler ABI info 2024-03-19T23:42:43,704 -- Detecting CXX compiler ABI info - done 2024-03-19T23:42:43,746 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-03-19T23:42:43,747 -- Detecting CXX compile features 2024-03-19T23:42:43,750 -- Detecting CXX compile features - done 2024-03-19T23:42:43,783 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-03-19T23:42:43,854 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-03-19T23:42:44,161 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-03-19T23:42:44,167 -- Found Threads: TRUE 2024-03-19T23:42:44,179 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-03-19T23:42:44,279 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-03-19T23:42:44,279 -- ARM detected 2024-03-19T23:42:44,282 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-03-19T23:42:44,594 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-03-19T23:42:44,632 CMake Warning (dev) at CMakeLists.txt:23 (install): 2024-03-19T23:42:44,633 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-03-19T23:42:44,633 This warning is for project developers. Use -Wno-dev to suppress it. 2024-03-19T23:42:44,634 CMake Warning (dev) at CMakeLists.txt:32 (install): 2024-03-19T23:42:44,634 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-03-19T23:42:44,635 This warning is for project developers. Use -Wno-dev to suppress it. 2024-03-19T23:42:44,636 -- Configuring done 2024-03-19T23:42:44,693 -- Generating done 2024-03-19T23:42:44,711 -- Build files have been written to: /tmp/tmpcjtatoia/build 2024-03-19T23:42:44,723 *** Building project with Ninja... 2024-03-19T23:42:47,964 [1/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/ggml-alloc.c 2024-03-19T23:42:48,207 [2/20] cd /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-03-19T23:42:48,208 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-03-19T23:42:48,361 [3/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/build-info.cpp 2024-03-19T23:42:52,116 [4/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/ggml-backend.c 2024-03-19T23:43:02,754 [5/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/. -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/sampling.cpp 2024-03-19T23:43:04,615 [6/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -std=gnu++11 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/unicode.cpp 2024-03-19T23:43:06,613 [7/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/. -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/console.cpp 2024-03-19T23:43:18,076 [8/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/. -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/grammar-parser.cpp 2024-03-19T23:43:24,959 [9/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/. -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/train.cpp 2024-03-19T23:43:33,636 [10/20] /usr/bin/c++ -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/examples/quantize/../../common -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/examples/quantize/quantize.cpp 2024-03-19T23:43:38,446 [11/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/ggml-quants.c 2024-03-19T23:43:42,501 [12/20] /usr/bin/c++ -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/. -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/examples/imatrix/imatrix.cpp 2024-03-19T23:43:44,213 [13/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/. -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/common.cpp 2024-03-19T23:43:44,214 In file included from /usr/include/c++/12/vector:70, 2024-03-19T23:43:44,214 from /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/grammar-parser.h:14, 2024-03-19T23:43:44,215 from /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/sampling.h:5, 2024-03-19T23:43:44,216 from /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/common.h:7, 2024-03-19T23:43:44,217 from /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/common.cpp:1: 2024-03-19T23:43:44,218 /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]’: 2024-03-19T23:43:44,218 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-03-19T23:43:44,219 439 | vector<_Tp, _Alloc>:: 2024-03-19T23:43:44,219 | ^~~~~~~~~~~~~~~~~~~ 2024-03-19T23:43:44,220 /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]’: 2024-03-19T23:43:44,220 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-03-19T23:43:44,221 In file included from /usr/include/c++/12/vector:64: 2024-03-19T23:43:44,222 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-03-19T23:43:44,222 inlined from ‘bool gpt_params_find_arg(int, char**, gpt_params&, int&, bool&)’ at /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/common.cpp:1162:38: 2024-03-19T23:43:44,223 /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 2024-03-19T23:43:44,224 1287 | _M_realloc_insert(end(), __x); 2024-03-19T23:43:44,224 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-03-19T23:43:44,225 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-03-19T23:43:44,226 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/common/common.cpp:1229:41: 2024-03-19T23:43:44,227 /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 2024-03-19T23:43:44,228 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-03-19T23:43:44,229 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:43:56,360 [14/20] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/ggml.c 2024-03-19T23:43:56,703 [15/20] : && /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 && : 2024-03-19T23:45:01,247 [16/20] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/. -O3 -DNDEBUG -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 -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-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp 2024-03-19T23:45:01,248 In file included from /usr/include/c++/12/vector:64, 2024-03-19T23:45:01,249 from /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.h:985, 2024-03-19T23:45:01,249 from /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:2: 2024-03-19T23:45:01,249 /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]’: 2024-03-19T23:45:01,250 /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 2024-03-19T23:45:01,250 673 | vector(initializer_list __l, 2024-03-19T23:45:01,251 | ^~~~~~ 2024-03-19T23:45:01,251 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/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*)’: 2024-03-19T23:45:01,252 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4209:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,253 4209 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,253 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,254 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4213:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,254 4213 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,255 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,255 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4215:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,256 4215 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-19T23:45:01,257 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,257 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4218:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,258 4218 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,259 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,259 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4252:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,259 4252 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,260 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,260 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4253:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,261 4253 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-03-19T23:45:01,261 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,261 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4254:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,262 4254 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,262 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,263 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4270:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,263 4270 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,264 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,265 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4272:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,265 4272 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,266 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,266 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4273:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,267 4273 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,267 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,268 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4284:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,268 4284 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,269 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,269 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4286:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,270 4286 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,270 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,270 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4287:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,271 4287 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,271 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,272 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4291:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,272 4291 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,272 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,273 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4298:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,273 4298 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,274 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,275 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4302:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,275 4302 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,276 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,276 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4303:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,277 4303 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,277 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,278 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4305:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,278 4305 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-19T23:45:01,279 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,279 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4307:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,280 4307 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-03-19T23:45:01,281 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,281 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4319:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,281 4319 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,282 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,282 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4320:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,283 4320 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,283 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,283 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4323:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,284 4323 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-03-19T23:45:01,284 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,285 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4324:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,285 4324 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-03-19T23:45:01,286 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,286 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4328:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,287 4328 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,287 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,288 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4330:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,288 4330 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-03-19T23:45:01,289 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,289 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4336:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,290 4336 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,290 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,291 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4337:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,291 4337 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-03-19T23:45:01,291 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,292 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4341:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,292 4341 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,293 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,293 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4342:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,294 4342 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,294 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,294 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4343:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,295 4343 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,295 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,296 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4353:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,296 4353 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,297 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,297 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4358:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,298 4358 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,298 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,299 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4359:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,299 4359 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-03-19T23:45:01,300 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,301 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4362:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,301 4362 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,301 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,302 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4364:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,302 4364 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,302 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,303 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4373:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,303 4373 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,304 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,304 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4376:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,305 4376 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,305 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,306 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4377:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,306 4377 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,307 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,307 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4378:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,308 4378 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,308 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,309 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4387:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,309 4387 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,310 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,310 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4403:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,311 4403 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,311 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,311 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4405:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,312 4405 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {64}); 2024-03-19T23:45:01,312 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,313 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4409:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,313 4409 | layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), {64}); 2024-03-19T23:45:01,313 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,314 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4415:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,314 4415 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,315 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,315 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4416:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,316 4416 | model.type_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_vocab_type}); 2024-03-19T23:45:01,316 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,317 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4418:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,317 4418 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-03-19T23:45:01,318 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,318 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4421:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,319 4421 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,319 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,320 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4422:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,321 4422 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,321 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,321 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4431:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,322 4431 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,322 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,323 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4432:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,323 4432 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-03-19T23:45:01,323 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,324 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4434:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,324 4434 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,325 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,325 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4435:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,326 4435 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-03-19T23:45:01,326 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,327 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4437:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,327 4437 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,328 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,328 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4438:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,329 4438 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-03-19T23:45:01,329 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,330 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4440:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,330 4440 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-03-19T23:45:01,331 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,331 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4443:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,332 4443 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,332 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,332 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4445:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,333 4445 | layer.attn_out_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,333 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,333 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4449:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,334 4449 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,334 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,335 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4452:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,335 4452 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-03-19T23:45:01,336 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,336 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4453:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,337 4453 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-03-19T23:45:01,337 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,338 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4455:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,338 4455 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-03-19T23:45:01,339 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,339 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4457:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,340 4457 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,340 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,341 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4461:66: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,341 4461 | layer.layer_out_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_LAYER_OUT_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,342 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,342 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4466:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,342 4466 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,343 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,343 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4467:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,344 4467 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,344 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,345 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4468:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,346 4468 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,346 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,347 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4472:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,348 4472 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,348 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,349 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4473:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,349 4473 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,350 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,351 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4474:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,351 4474 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,352 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,352 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4484:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,353 4484 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,353 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,354 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4487:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,354 4487 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-03-19T23:45:01,355 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,356 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4492:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,356 4492 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,357 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,357 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4495:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,358 4495 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,358 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,359 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4498:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,359 4498 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,360 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,361 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4499:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,361 4499 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-03-19T23:45:01,362 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,362 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4504:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,363 4504 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,364 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,364 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4508:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,365 4508 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,366 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,366 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4509:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,367 4509 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, false); 2024-03-19T23:45:01,367 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,368 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4511:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,368 4511 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-19T23:45:01,369 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,369 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4513:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,370 4513 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-03-19T23:45:01,370 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,371 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4529:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,372 4529 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}, false); 2024-03-19T23:45:01,372 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,373 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4537:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,373 4537 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,374 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,375 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4541:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,375 4541 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, false); 2024-03-19T23:45:01,376 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,377 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4549:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,377 4549 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,378 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,379 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4553:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,379 4553 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,380 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,380 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4554:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,381 4554 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,381 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,382 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4555:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,382 4555 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,383 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,383 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4564:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,384 4564 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,384 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,385 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4567:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,385 4567 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,386 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,387 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4569:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,387 4569 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,388 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,388 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4573:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,389 4573 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}, false); 2024-03-19T23:45:01,389 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,390 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4575:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,391 4575 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}, false); 2024-03-19T23:45:01,391 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,392 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4577:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,392 4577 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,393 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,393 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4582:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,394 4582 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,394 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,395 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4587:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,395 4587 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,396 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,396 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4591:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,397 4591 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,398 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,398 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4592:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,399 4592 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,400 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,400 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4604:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,401 4604 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd*3}); 2024-03-19T23:45:01,402 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,402 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4609:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,403 4609 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2}); 2024-03-19T23:45:01,404 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,404 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4616:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,405 4616 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,405 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,406 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4620:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,407 4620 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,407 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,408 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4621:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,408 4621 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,409 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,409 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4632:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,410 4632 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,410 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,411 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4639:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,411 4639 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-03-19T23:45:01,412 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,412 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4645:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,413 4645 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-03-19T23:45:01,414 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,414 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4646:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,415 4646 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,416 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,416 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4651:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,417 4651 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,417 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,418 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4655:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,418 4655 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,419 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,419 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4656:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,420 4656 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,420 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,421 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4657:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,421 4657 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,422 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,423 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4658:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,423 4658 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-03-19T23:45:01,424 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,424 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4667:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,425 4667 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,426 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,426 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4668:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,427 4668 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,428 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,429 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4670:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,429 4670 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, false); 2024-03-19T23:45:01,430 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,430 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4674:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,431 4674 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,431 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,431 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4675:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,432 4675 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-03-19T23:45:01,432 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,433 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4677:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,434 4677 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,435 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,435 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4678:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,436 4678 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-03-19T23:45:01,437 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,438 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4680:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,438 4680 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,439 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,440 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4681:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,440 4681 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-03-19T23:45:01,441 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,442 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4687:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,443 4687 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,443 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,444 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4688:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,444 4688 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-03-19T23:45:01,445 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,446 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4696:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,446 4696 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,447 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,448 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4700:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,448 4700 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,449 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,450 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4701:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,450 4701 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,451 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,452 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4710:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,453 4710 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,453 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,454 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4715:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,455 4715 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,456 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,456 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4724:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,457 4724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,458 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,458 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4725:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,459 4725 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-03-19T23:45:01,459 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,460 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4729:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,460 4729 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,461 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,461 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4730:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,462 4730 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,463 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,463 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4731:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,464 4731 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,465 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,465 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4750:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,466 4750 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,466 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,467 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4752:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,468 4752 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,468 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,469 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4753:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,470 4753 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-03-19T23:45:01,471 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,471 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4761:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,471 4761 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,472 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,473 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4765:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,473 4765 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,474 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,474 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4766:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,475 4766 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,475 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,476 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4767:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,476 4767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,477 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,478 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4783:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,478 4783 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-03-19T23:45:01,479 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,479 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4788:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,480 4788 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-03-19T23:45:01,481 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,481 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4789:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,482 4789 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-03-19T23:45:01,482 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,483 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4797:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,484 4797 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,484 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,485 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4799:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,485 4799 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,486 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,486 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4800:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,487 4800 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,487 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,488 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4801:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,489 4801 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,489 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,490 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4810:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,490 4810 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,491 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,492 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4812:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,492 4812 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,493 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,493 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4813:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,494 4813 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,495 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,496 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4815:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,496 4815 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-03-19T23:45:01,497 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,498 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4817:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,498 4817 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,499 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,499 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4821:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,500 4821 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-03-19T23:45:01,500 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,501 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4822:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,501 4822 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,502 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,502 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4827:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,503 4827 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,503 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,504 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4831:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,505 4831 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,505 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,506 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4832:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,506 4832 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,507 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,508 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4841:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,509 4841 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,512 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,512 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4845:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,519 4845 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,531 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,531 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4851:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,532 4851 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,532 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,533 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4856:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,536 4856 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,536 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,537 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4859:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,537 4859 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,538 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,539 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4860:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,540 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 2024-03-19T23:45:01,541 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,543 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4875:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,545 4875 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,551 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,558 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4878:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,559 4878 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_k_gqa}); 2024-03-19T23:45:01,565 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,566 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4879:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,567 4879 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_v_gqa}); 2024-03-19T23:45:01,567 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,568 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4882:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,568 4882 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,569 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,570 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4883:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,570 4883 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,571 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,571 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4890:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,572 4890 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,572 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,573 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4894:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,573 4894 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,574 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,575 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4895:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,575 4895 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-03-19T23:45:01,576 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,576 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4897:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,577 4897 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-19T23:45:01,577 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,578 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4900:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,579 4900 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,579 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,580 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4913:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,580 4913 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,581 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,581 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4918:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,582 4918 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-03-19T23:45:01,582 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,583 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4923:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,583 4923 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-03-19T23:45:01,584 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,584 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4927:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,585 4927 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,586 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,586 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4928:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,587 4928 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-03-19T23:45:01,587 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,588 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4931:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,589 4931 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-03-19T23:45:01,589 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,590 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4934:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,591 4934 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-03-19T23:45:01,592 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,593 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4947:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,593 4947 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,594 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,594 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4951:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,595 4951 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,596 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,596 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4953:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,597 4953 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-03-19T23:45:01,598 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,598 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4956:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,599 4956 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,600 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,600 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4969:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,601 4969 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-03-19T23:45:01,602 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,602 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4971:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,603 4971 | layer.ssm_in = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, 2*d_inner}); 2024-03-19T23:45:01,604 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,605 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4973:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,606 4973 | layer.ssm_conv1d = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner}); 2024-03-19T23:45:01,606 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,607 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4974:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,608 4974 | layer.ssm_conv1d_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner}); 2024-03-19T23:45:01,609 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,610 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4976:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,610 4976 | layer.ssm_x = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_X, "weight", i), {d_inner, dt_rank + 2*d_state}); 2024-03-19T23:45:01,611 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,611 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4978:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,612 4978 | layer.ssm_dt = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_DT, "weight", i), {dt_rank, d_inner}); 2024-03-19T23:45:01,613 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,614 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4979:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,614 4979 | layer.ssm_dt_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_DT, "bias", i), {d_inner}); 2024-03-19T23:45:01,615 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,615 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4982:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,616 4982 | layer.ssm_a = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_A, i), {d_state, d_inner}); 2024-03-19T23:45:01,616 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,617 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4983:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,618 4983 | layer.ssm_d = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_D, i), {d_inner}); 2024-03-19T23:45:01,618 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,619 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4986:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,619 4986 | layer.ssm_out = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}); 2024-03-19T23:45:01,620 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,620 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4991:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,621 4991 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,622 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,622 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4995:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,623 4995 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-03-19T23:45:01,623 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,624 /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/vendor/llama.cpp/llama.cpp:4997:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-03-19T23:45:01,624 4997 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-03-19T23:45:01,625 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,626 In file included from /usr/include/c++/12/vector:70: 2024-03-19T23:45:01,626 /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]’: 2024-03-19T23:45:01,627 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-03-19T23:45:01,627 439 | vector<_Tp, _Alloc>:: 2024-03-19T23:45:01,628 | ^~~~~~~~~~~~~~~~~~~ 2024-03-19T23:45:01,628 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-03-19T23:45:01,629 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, 2024-03-19T23:45:01,629 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, 2024-03-19T23:45:01,630 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-03-19T23:45:01,631 /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 2024-03-19T23:45:01,631 1287 | _M_realloc_insert(end(), __x); 2024-03-19T23:45:01,632 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-03-19T23:45:01,633 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-03-19T23:45:01,634 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, 2024-03-19T23:45:01,634 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, 2024-03-19T23:45:01,635 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-03-19T23:45:01,636 /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 2024-03-19T23:45:01,636 1287 | _M_realloc_insert(end(), __x); 2024-03-19T23:45:01,637 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-03-19T23:45:01,711 [17/20] : && /usr/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 && : 2024-03-19T23:45:02,030 [18/20] : && /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 && : 2024-03-19T23:45:02,163 [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 && : 2024-03-19T23:45:02,460 [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 && : 2024-03-19T23:45:02,465 *** Installing project into wheel... 2024-03-19T23:45:02,502 -- Install configuration: "Release" 2024-03-19T23:45:02,507 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-03-19T23:45:02,510 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-03-19T23:45:02,513 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/include/ggml.h 2024-03-19T23:45:02,518 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/include/ggml-alloc.h 2024-03-19T23:45:02,520 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/include/ggml-backend.h 2024-03-19T23:45:02,523 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/lib/libllama.a 2024-03-19T23:45:02,553 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/include/llama.h 2024-03-19T23:45:02,558 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/bin/convert.py 2024-03-19T23:45:02,562 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/bin/convert-lora-to-ggml.py 2024-03-19T23:45:02,567 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/bin/quantize 2024-03-19T23:45:02,649 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/bin/imatrix 2024-03-19T23:45:02,735 -- Installing: /tmp/tmpcjtatoia/wheel/platlib/llama_cpp/libllama.a 2024-03-19T23:45:02,763 -- Installing: /tmp/pip-wheel-tcrba1f1/llama-cpp-conv_e29464bb267848f79d3f3451c4857e89/llama_cpp/libllama.a 2024-03-19T23:45:02,796 *** Making wheel... 2024-03-19T23:45:04,432 *** Created llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_36_armv7l.whl... 2024-03-19T23:45:04,491 Building wheel for llama-cpp-conv (pyproject.toml): finished with status 'done' 2024-03-19T23:45:04,523 Created wheel for llama-cpp-conv: filename=llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_36_armv7l.whl size=2674043 sha256=c851c1100f9c04f112ebaaa0bb42bbc9ddbc7760a84e8d13e6610cddccde1912 2024-03-19T23:45:04,524 Stored in directory: /tmp/pip-ephem-wheel-cache-reyp3ghl/wheels/a5/e5/eb/cde7e58e1594d068a6930c37b29026a82c92d387fd268946f3 2024-03-19T23:45:04,544 Successfully built llama-cpp-conv 2024-03-19T23:45:04,624 Removed build tracker: '/tmp/pip-build-tracker-wmlj8lhl'