2024-02-14T01:22:21,251 Created temporary directory: /tmp/pip-build-tracker-7nru3snc 2024-02-14T01:22:21,253 Initialized build tracking at /tmp/pip-build-tracker-7nru3snc 2024-02-14T01:22:21,254 Created build tracker: /tmp/pip-build-tracker-7nru3snc 2024-02-14T01:22:21,254 Entered build tracker: /tmp/pip-build-tracker-7nru3snc 2024-02-14T01:22:21,255 Created temporary directory: /tmp/pip-wheel-l4yrl2zr 2024-02-14T01:22:21,263 Created temporary directory: /tmp/pip-ephem-wheel-cache-t1ze1wuv 2024-02-14T01:22:21,287 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-14T01:22:21,291 2 location(s) to search for versions of llama-core: 2024-02-14T01:22:21,291 * https://pypi.org/simple/llama-core/ 2024-02-14T01:22:21,291 * https://www.piwheels.org/simple/llama-core/ 2024-02-14T01:22:21,292 Fetching project page and analyzing links: https://pypi.org/simple/llama-core/ 2024-02-14T01:22:21,292 Getting page https://pypi.org/simple/llama-core/ 2024-02-14T01:22:21,294 Found index url https://pypi.org/simple/ 2024-02-14T01:22:21,504 Fetched page https://pypi.org/simple/llama-core/ as application/vnd.pypi.simple.v1+json 2024-02-14T01:22:21,509 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/0c/3f/cd0eb8df269d2fef873ffcc04fe040ac5db0fea04d4f2cb4faf7cbfafac1/llama_core-0.0.1-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,510 Found link https://files.pythonhosted.org/packages/54/18/cfcca142a70d8179270564bb0d3ecdea14e025ee22af9ae7c36940515572/llama_core-0.0.1.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.1 2024-02-14T01:22:21,510 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/ec/7b/0b48decfb9fbc2076f5015faa1c62e75118c4ade6eb578d14c42eaa09c70/llama_core-0.0.2-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,511 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/89/25/f230d101e143cb48af28f86d5a3a60e5e6b37c7f93e3c646ca0151eda959/llama_core-0.0.2-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,512 Found link https://files.pythonhosted.org/packages/13/e0/942cd90aa6099469476699a34730f93ae98eec75637bcaaae05f30b671e5/llama_core-0.0.2.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.2 2024-02-14T01:22:21,513 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/16/8f/8bdffd743f5b585d172348cb0b4898599d502dcc4ca9776d1d59ddf04b0f/llama_core-0.0.3-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,513 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/5b/40/9058f432251845d67ea827068977a063ab628a9f20770c6d993705bef6ab/llama_core-0.0.3-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,514 Found link https://files.pythonhosted.org/packages/45/0c/87c799e77c52feb34e96629c75e320f9f0251ba248421a71b31eae61c0d5/llama_core-0.0.3.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.3 2024-02-14T01:22:21,515 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/76/a1/730cdb64b7d7b7f88ff9b21d8e7378046114edaacaf601c1198461658645/llama_core-0.0.4-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,516 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/5d/ee/a6843bed253fed2ce18cbbae670aa9491b1e551e9a947742b5c6e044d232/llama_core-0.0.4-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,517 Found link https://files.pythonhosted.org/packages/13/b1/8a7735d888055a2ecc20303aa25701315bc5473bb13dc7ea641a8f9f127c/llama_core-0.0.4.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.4 2024-02-14T01:22:21,517 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/04/58/88367add4d3b38a361eac6873fcb80ca940f1ca5b6a6be2c1cfef2e41f6c/llama_core-0.0.5-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,518 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/d6/e6/bc61cad7e72c6b93ee0a80cf16055c9715733990211ffed07589136d2ee4/llama_core-0.0.5-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,519 Found link https://files.pythonhosted.org/packages/7b/a8/ae13de98bba0e3ed52b92ccf36729bc0b0096416208bdc8627b44d4f3e9e/llama_core-0.0.5.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.5 2024-02-14T01:22:21,520 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/9b/12/ed0e3cc2464898a1484c03e677fa63bccfc3b4c74193b98742e8aaa8795b/llama_core-0.0.6-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,520 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/fe/2b/3ab1508dc587980138deecb30e4e90ba3c5112f9b80271c4809e44281595/llama_core-0.0.6-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,521 Found link https://files.pythonhosted.org/packages/35/2e/a977614705b55c4a06e3d06f63e9c9c8e4bcdc09a660c94876f8cbee2ebb/llama_core-0.0.6.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.6 2024-02-14T01:22:21,522 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/1e/2c/caad32100a65f1a1285489b1361696f3ea09fc275fdcd66434e37e472157/llama_core-0.0.7-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,522 Skipping link: No binaries permitted for llama-core: https://files.pythonhosted.org/packages/4a/b4/398b92a7301970f847235a8a381ef09bf214b94e8a1701a34ab6037b11b0/llama_core-0.0.7-cp312-cp312-macosx_11_0_x86_64.whl (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,523 Found link https://files.pythonhosted.org/packages/65/0d/0c07e57c2c6e3dd379c3475d8e5d6edf43d3b872489593687d4a55a6f133/llama_core-0.0.7.tar.gz (from https://pypi.org/simple/llama-core/) (requires-python:>=3.8), version: 0.0.7 2024-02-14T01:22:21,524 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-core/ 2024-02-14T01:22:21,525 Getting page https://www.piwheels.org/simple/llama-core/ 2024-02-14T01:22:21,526 Found index url https://www.piwheels.org/simple/ 2024-02-14T01:22:21,678 Fetched page https://www.piwheels.org/simple/llama-core/ as text/html 2024-02-14T01:22:21,683 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.6-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=f7b899c8dbafc2241a284644157da3c26143a5fe822da5558b3a31bf20a1eeac (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,683 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.6-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=66313863d5dadfe182cf56651ec416724f87b902c40dac00ee80b9fdf0839348 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,684 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.5-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=a66ba2119016dc40194667275a18776e662fab4f1a5511f64bfd044779d92f81 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,685 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.5-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=e4b10f5dbcb73b20ab2a934873a0f73b097f1d7b955e90fdf88880f1801c6b0e (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,685 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.4-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=9f62271a9271c6f1f31e63c136ec95db7f9182737b2e8c15951fee2b79e08bab (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,686 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.4-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=ffd28806ae94f9a8563fa31b5df3f31f264386493beb96fad0ffc2c551802572 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,687 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.3-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=60e4da9a7c59f727c521b26a7e2959af9d5e84a96fe28d9c5e31f658b74bc683 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,687 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.3-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=e4d3e1d0928d8e196bb3629af0ffc3c81c6cc27b7829b3d237e1754e54e00cc6 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,687 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.2-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=39b6da3d8b2c0a1bf4fe8ea9c6e0c25dc5ee291ba2d893e01751a684696ada6f (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,688 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.2-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=80df05f3984df31d62d543508bcf72719f7819fc924f4fe4aa2b8a14a3151fb5 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,688 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.1-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=0457a9c9fad48014762fe5e8eaacf08e7a030a8fa375ced00308fc00a32294d5 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,689 Skipping link: No binaries permitted for llama-core: https://www.piwheels.org/simple/llama-core/llama_core-0.0.1-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=77646f382b23fba3fee5b1c6ca2af87609b49328e9c70e637104fb842bd80805 (from https://www.piwheels.org/simple/llama-core/) (requires-python:>=3.8) 2024-02-14T01:22:21,690 Skipping link: not a file: https://www.piwheels.org/simple/llama-core/ 2024-02-14T01:22:21,691 Skipping link: not a file: https://pypi.org/simple/llama-core/ 2024-02-14T01:22:21,711 Given no hashes to check 1 links for project 'llama-core': discarding no candidates 2024-02-14T01:22:21,730 Collecting llama-core==0.0.7 2024-02-14T01:22:21,733 Created temporary directory: /tmp/pip-unpack-rhumdmx7 2024-02-14T01:22:22,212 Downloading llama_core-0.0.7.tar.gz (10.6 MB) 2024-02-14T01:22:25,493 Added llama-core==0.0.7 from https://files.pythonhosted.org/packages/65/0d/0c07e57c2c6e3dd379c3475d8e5d6edf43d3b872489593687d4a55a6f133/llama_core-0.0.7.tar.gz to build tracker '/tmp/pip-build-tracker-7nru3snc' 2024-02-14T01:22:25,497 Created temporary directory: /tmp/pip-build-env-ck1y3hgs 2024-02-14T01:22:25,502 Installing build dependencies: started 2024-02-14T01:22:25,503 Running command pip subprocess to install build dependencies 2024-02-14T01:22:26,682 Using pip 23.3.1 from /home/piwheels/.local/lib/python3.11/site-packages/pip (python 3.11) 2024-02-14T01:22:27,221 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-02-14T01:22:27,745 Collecting scikit-build-core[pyproject] 2024-02-14T01:22:27,763 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.0-py3-none-any.whl (139 kB) 2024-02-14T01:22:28,051 Collecting packaging>=20.9 (from scikit-build-core[pyproject]) 2024-02-14T01:22:28,064 Using cached https://www.piwheels.org/simple/packaging/packaging-23.2-py3-none-any.whl (53 kB) 2024-02-14T01:22:28,166 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]) 2024-02-14T01:22:28,179 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-02-14T01:22:28,250 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]) 2024-02-14T01:22:28,264 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-02-14T01:22:30,966 Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata 2024-02-14T01:22:31,672 Successfully installed packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.0 2024-02-14T01:22:31,932 [notice] A new release of pip is available: 23.3.1 -> 24.0 2024-02-14T01:22:31,933 [notice] To update, run: python3 -m pip install --upgrade pip 2024-02-14T01:22:32,167 Installing build dependencies: finished with status 'done' 2024-02-14T01:22:32,170 Getting requirements to build wheel: started 2024-02-14T01:22:32,172 Running command Getting requirements to build wheel 2024-02-14T01:22:32,591 Getting requirements to build wheel: finished with status 'done' 2024-02-14T01:22:32,618 Created temporary directory: /tmp/pip-modern-metadata-a5ohen0e 2024-02-14T01:22:32,620 Preparing metadata (pyproject.toml): started 2024-02-14T01:22:32,622 Running command Preparing metadata (pyproject.toml) 2024-02-14T01:22:33,117 *** scikit-build-core 0.8.0 using CMake 3.25.1 (metadata_wheel) 2024-02-14T01:22:33,207 Preparing metadata (pyproject.toml): finished with status 'done' 2024-02-14T01:22:33,212 Source in /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb has version 0.0.7, which satisfies requirement llama-core==0.0.7 from https://files.pythonhosted.org/packages/65/0d/0c07e57c2c6e3dd379c3475d8e5d6edf43d3b872489593687d4a55a6f133/llama_core-0.0.7.tar.gz 2024-02-14T01:22:33,213 Removed llama-core==0.0.7 from https://files.pythonhosted.org/packages/65/0d/0c07e57c2c6e3dd379c3475d8e5d6edf43d3b872489593687d4a55a6f133/llama_core-0.0.7.tar.gz from build tracker '/tmp/pip-build-tracker-7nru3snc' 2024-02-14T01:22:33,219 Created temporary directory: /tmp/pip-unpack-nh5aqapo 2024-02-14T01:22:33,220 Created temporary directory: /tmp/pip-unpack-u8fegv91 2024-02-14T01:22:33,227 Building wheels for collected packages: llama-core 2024-02-14T01:22:33,231 Created temporary directory: /tmp/pip-wheel-qu6ru5e2 2024-02-14T01:22:33,232 Destination directory: /tmp/pip-wheel-qu6ru5e2 2024-02-14T01:22:33,234 Building wheel for llama-core (pyproject.toml): started 2024-02-14T01:22:33,235 Running command Building wheel for llama-core (pyproject.toml) 2024-02-14T01:22:33,723 *** scikit-build-core 0.8.0 using CMake 3.25.1 (wheel) 2024-02-14T01:22:33,742 *** Configuring CMake... 2024-02-14T01:22:33,836 loading initial cache file /tmp/tmp1ubcjt15/build/CMakeInit.txt 2024-02-14T01:22:34,109 -- The C compiler identification is GNU 12.2.0 2024-02-14T01:22:34,416 -- The CXX compiler identification is GNU 12.2.0 2024-02-14T01:22:34,471 -- Detecting C compiler ABI info 2024-02-14T01:22:34,753 -- Detecting C compiler ABI info - done 2024-02-14T01:22:34,790 -- Check for working C compiler: /usr/bin/cc - skipped 2024-02-14T01:22:34,792 -- Detecting C compile features 2024-02-14T01:22:34,794 -- Detecting C compile features - done 2024-02-14T01:22:34,814 -- Detecting CXX compiler ABI info 2024-02-14T01:22:35,130 -- Detecting CXX compiler ABI info - done 2024-02-14T01:22:35,169 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-02-14T01:22:35,170 -- Detecting CXX compile features 2024-02-14T01:22:35,173 -- Detecting CXX compile features - done 2024-02-14T01:22:35,203 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-14T01:22:35,264 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-02-14T01:22:35,578 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-02-14T01:22:35,582 -- Found Threads: TRUE 2024-02-14T01:22:35,593 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-02-14T01:22:35,694 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-02-14T01:22:35,695 -- ARM detected 2024-02-14T01:22:35,698 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-02-14T01:22:36,008 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-02-14T01:22:36,038 CMake Warning (dev) at CMakeLists.txt:17 (install): 2024-02-14T01:22:36,038 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-14T01:22:36,039 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-14T01:22:36,040 CMake Warning (dev) at CMakeLists.txt:25 (install): 2024-02-14T01:22:36,040 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-02-14T01:22:36,041 This warning is for project developers. Use -Wno-dev to suppress it. 2024-02-14T01:22:36,047 -- Configuring done 2024-02-14T01:22:36,129 -- Generating done 2024-02-14T01:22:36,155 -- Build files have been written to: /tmp/tmp1ubcjt15/build 2024-02-14T01:22:36,171 *** Building project with Ninja... 2024-02-14T01:22:36,562 [1/22] cd /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/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-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-02-14T01:22:36,563 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-02-14T01:22:36,731 [2/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/build-info.cpp 2024-02-14T01:22:38,914 [3/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/ggml-alloc.c 2024-02-14T01:22:42,337 [4/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/ggml-backend.c 2024-02-14T01:22:46,779 [5/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/console.cpp 2024-02-14T01:22:49,463 [6/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/sampling.cpp 2024-02-14T01:22:57,645 [7/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/grammar-parser.cpp 2024-02-14T01:23:05,606 [8/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/train.cpp 2024-02-14T01:23:05,674 [9/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wno-cast-qual -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/llava.cpp 2024-02-14T01:23:14,398 [10/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/ggml-quants.c 2024-02-14T01:23:18,003 [11/22] /usr/bin/c++ -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/../../common -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/llava-cli.cpp 2024-02-14T01:23:32,535 [12/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/common.cpp 2024-02-14T01:23:32,535 In file included from /usr/include/c++/12/vector:70, 2024-02-14T01:23:32,536 from /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/grammar-parser.h:14, 2024-02-14T01:23:32,537 from /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/sampling.h:5, 2024-02-14T01:23:32,538 from /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/common.h:7, 2024-02-14T01:23:32,539 from /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/common.cpp:1: 2024-02-14T01:23:32,540 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const llama_model_kv_override&}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-02-14T01:23:32,540 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-14T01:23:32,541 439 | vector<_Tp, _Alloc>:: 2024-02-14T01:23:32,542 | ^~~~~~~~~~~~~~~~~~~ 2024-02-14T01:23:32,543 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-02-14T01:23:32,544 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-14T01:23:32,545 In file included from /usr/include/c++/12/vector:64: 2024-02-14T01:23:32,546 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-14T01:23:32,546 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/common.cpp:850:42: 2024-02-14T01:23:32,547 /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-14T01:23:32,548 1287 | _M_realloc_insert(end(), __x); 2024-02-14T01:23:32,549 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-14T01:23:32,550 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-02-14T01:23:32,550 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/common/common.cpp:895:41: 2024-02-14T01:23:32,551 /usr/include/c++/12/bits/vector.tcc:123:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-14T01:23:32,552 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-02-14T01:23:32,553 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:23:39,333 [13/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/ggml.c 2024-02-14T01:23:39,573 [14/22] : && /usr/bin/cc -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libggml_shared.so -o vendor/llama.cpp/libggml_shared.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o && : 2024-02-14T01:23:39,708 [15/22] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/libggml_static.a && /usr/bin/ar qc vendor/llama.cpp/libggml_static.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && : 2024-02-14T01:23:57,702 [16/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/../.. -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/../../common -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wno-cast-qual -MD -MT vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o -MF vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o.d -o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/examples/llava/clip.cpp 2024-02-14T01:23:58,015 [17/22] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/examples/llava/libllava_static.a && /usr/bin/ar qc vendor/llama.cpp/examples/llava/libllava_static.a vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o && /usr/bin/ranlib vendor/llama.cpp/examples/llava/libllava_static.a && : 2024-02-14T01:24:29,893 [18/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp 2024-02-14T01:24:29,893 In file included from /usr/include/c++/12/vector:64, 2024-02-14T01:24:29,894 from /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.h:908, 2024-02-14T01:24:29,894 from /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:2: 2024-02-14T01:24:29,895 /usr/include/c++/12/bits/stl_vector.h: In function ‘std::vector<_Tp, _Alloc>::vector(std::initializer_list<_Tp>, const allocator_type&) [with _Tp = long long int; _Alloc = std::allocator]’: 2024-02-14T01:24:29,895 /usr/include/c++/12/bits/stl_vector.h:673:7: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,896 673 | vector(initializer_list __l, 2024-02-14T01:24:29,896 | ^~~~~~ 2024-02-14T01:24:29,897 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp: In function ‘bool llm_load_tensors(llama_model_loader&, llama_model&, int, llama_split_mode, int, const float*, bool, llama_progress_callback, void*)’: 2024-02-14T01:24:29,897 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3528:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,898 3528 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,898 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,899 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3532:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,899 3532 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,900 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,900 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3533:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,901 3533 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,902 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,902 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3563:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,902 3563 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:29,903 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,903 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3564:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,903 3564 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-14T01:24:29,904 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,904 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3565:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,904 3565 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:29,905 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,905 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3581:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,906 3581 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,907 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,907 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3583:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,907 3583 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,908 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,908 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3584:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,909 3584 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,909 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,910 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3596:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,910 3596 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:29,911 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,912 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3604:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,912 3604 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:29,912 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,913 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3609:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,913 3609 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,913 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,914 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3613:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,914 3613 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,914 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,915 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3614:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,916 3614 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:29,917 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,917 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3616:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,918 3616 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,918 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,919 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3618:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,920 3618 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-02-14T01:24:29,920 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,921 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3630:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,921 3630 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:29,922 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,922 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3633:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,923 3633 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}); 2024-02-14T01:24:29,923 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,924 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3634:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,924 3634 | layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i), {n_embd}); 2024-02-14T01:24:29,925 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,925 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3637:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,926 3637 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-14T01:24:29,926 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,926 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3638:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,927 3638 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:29,928 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,928 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3641:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,929 3641 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:29,929 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,930 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3646:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,930 3646 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,931 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,931 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3647:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,932 3647 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-14T01:24:29,932 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,933 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3651:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,934 3651 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,934 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,935 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3652:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,935 3652 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:29,936 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,936 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3653:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,937 3653 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,937 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,938 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3665:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,938 3665 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-14T01:24:29,939 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,939 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3669:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,940 3669 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-14T01:24:29,940 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,941 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3671:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,942 3671 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:29,942 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,943 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3674:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,944 3674 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-14T01:24:29,944 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,945 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3683:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,945 3683 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,946 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,947 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3686:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,947 3686 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,948 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,948 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3687:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,948 3687 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:29,949 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,949 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3688:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,950 3688 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,950 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,951 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3698:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,952 3698 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:29,952 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,953 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3703:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,954 3703 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:29,954 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,955 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3704:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,956 3704 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-14T01:24:29,956 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,957 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3707:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,957 3707 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-14T01:24:29,958 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,959 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3709:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,960 3709 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:29,960 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,961 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3712:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,961 3712 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:29,961 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,962 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3715:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,962 3715 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {64}); 2024-02-14T01:24:29,963 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,963 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3716:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,964 3716 | layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias", i), {64}); 2024-02-14T01:24:29,965 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,965 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3719:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,966 3719 | layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), {64}); 2024-02-14T01:24:29,967 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,967 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3724:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,968 3724 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,969 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,969 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3725:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,970 3725 | model.tok_norm = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,970 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,971 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3726:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,972 3726 | model.tok_norm_b = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-02-14T01:24:29,973 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,973 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3730:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,974 3730 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,974 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,974 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3731:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,975 3731 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:29,975 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,976 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3732:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,976 3732 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,977 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,977 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3741:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,978 3741 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:29,979 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,979 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3742:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,980 3742 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:29,980 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,981 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3744:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,982 3744 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-14T01:24:29,982 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,983 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3745:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,984 3745 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-02-14T01:24:29,984 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,985 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3748:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,986 3748 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-02-14T01:24:29,986 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,987 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3750:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,987 3750 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:29,988 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,988 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3754:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,988 3754 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-14T01:24:29,989 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,989 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3762:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,990 3762 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,991 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,991 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3766:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,992 3766 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:29,993 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,993 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3767:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,994 3767 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:29,994 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,995 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3776:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,996 3776 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:29,996 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,997 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3778:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,998 3778 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-02-14T01:24:29,998 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:29,999 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3779:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:29,999 3779 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,000 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,001 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3786:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,001 3786 | layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false); 2024-02-14T01:24:30,002 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,002 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3791:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,003 3791 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,004 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,005 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3795:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,006 3795 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:30,006 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,007 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3796:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,008 3796 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,009 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,010 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3797:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,010 3797 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,011 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,011 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3806:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,012 3806 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:30,013 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,014 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3807:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,014 3807 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:30,014 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,015 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3809:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,015 3809 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,016 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,016 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3810:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,017 3810 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:30,018 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,018 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3816:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,019 3816 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}, false); 2024-02-14T01:24:30,020 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,021 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3820:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,022 3820 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:30,022 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,023 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3824:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,024 3824 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:30,025 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,025 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3829:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,026 3829 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,027 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,028 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3833:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,029 3833 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,029 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,030 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3834:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,030 3834 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,030 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,031 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3843:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,031 3843 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:30,032 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,032 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3846:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,033 3846 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd*3}); 2024-02-14T01:24:30,033 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,034 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3851:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,035 3851 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2}); 2024-02-14T01:24:30,036 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,036 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3853:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,037 3853 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff/2}); 2024-02-14T01:24:30,038 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,039 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3858:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,039 3858 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,040 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,041 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3862:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,041 3862 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,042 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,043 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3863:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,043 3863 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,044 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,044 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3872:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,044 3872 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:30,045 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,045 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3876:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,046 3876 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:30,047 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,047 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3877:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,048 3877 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,049 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,050 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3881:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,051 3881 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-14T01:24:30,052 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,052 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3882:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,053 3882 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-14T01:24:30,054 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,054 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3887:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,055 3887 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-02-14T01:24:30,056 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,057 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3893:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,058 3893 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,058 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,059 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3897:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,059 3897 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,060 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,060 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3898:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,061 3898 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:30,061 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,062 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3899:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,062 3899 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,063 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,064 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3900:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,064 3900 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-02-14T01:24:30,065 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,066 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3909:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,066 3909 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:30,067 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,067 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3910:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,068 3910 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:30,069 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,069 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3912:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,070 3912 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, false); 2024-02-14T01:24:30,071 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,071 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3916:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,072 3916 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,072 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,073 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3917:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,073 3917 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-02-14T01:24:30,074 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,074 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3919:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,075 3919 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:30,076 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,077 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3920:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,077 3920 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-02-14T01:24:30,078 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,079 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3922:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,080 3922 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:30,081 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,081 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3923:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,082 3923 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-02-14T01:24:30,083 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,083 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3926:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,084 3926 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,085 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,086 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3929:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,086 3929 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-02-14T01:24:30,087 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,087 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3930:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,088 3930 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-14T01:24:30,089 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,089 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3933:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,090 3933 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-14T01:24:30,090 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,091 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3938:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,092 3938 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,093 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,093 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3942:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,094 3942 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,096 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,097 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3943:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,098 3943 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,099 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,101 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3952:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,102 3952 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-02-14T01:24:30,103 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,105 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3954:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,106 3954 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,107 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,107 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3955:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,108 3955 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:30,108 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,109 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3959:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,109 3959 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-02-14T01:24:30,110 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,111 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3966:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,112 3966 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,112 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,113 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3967:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,114 3967 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-02-14T01:24:30,115 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,116 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3971:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,116 3971 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,117 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,118 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3972:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,118 3972 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:30,119 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,120 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3973:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,121 3973 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,122 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,122 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3988:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,123 3988 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,123 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,124 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:3998:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,124 3998 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-02-14T01:24:30,125 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,126 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4003:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,126 4003 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,127 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,128 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4007:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,129 4007 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,130 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,132 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4008:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,133 4008 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:30,134 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,135 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4009:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,136 4009 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,138 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,138 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4019:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,139 4019 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-02-14T01:24:30,140 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,141 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4024:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,141 4024 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-02-14T01:24:30,141 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,142 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4031:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,142 4031 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-02-14T01:24:30,143 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,143 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4039:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,144 4039 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,144 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,145 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4041:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,146 4041 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,147 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,147 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4042:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,148 4042 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-02-14T01:24:30,149 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,149 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4043:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,150 4043 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,150 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,151 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4055:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,152 4055 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-02-14T01:24:30,152 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,153 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4069:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,153 4069 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,154 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,154 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4073:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,155 4073 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-02-14T01:24:30,155 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,156 /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/vendor/llama.cpp/llama.cpp:4074:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-02-14T01:24:30,156 4074 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-02-14T01:24:30,157 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,157 In file included from /usr/include/c++/12/vector:70: 2024-02-14T01:24:30,158 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const double&}; _Tp = double; _Alloc = std::allocator]’: 2024-02-14T01:24:30,159 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-02-14T01:24:30,159 439 | vector<_Tp, _Alloc>:: 2024-02-14T01:24:30,160 | ^~~~~~~~~~~~~~~~~~~ 2024-02-14T01:24:30,161 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-14T01:24:30,162 inlined from ‘std::back_insert_iterator<_Container>& std::back_insert_iterator<_Container>::operator=(const typename _Container::value_type&) [with _Container = std::vector]’ at /usr/include/c++/12/bits/stl_iterator.h:735:22, 2024-02-14T01:24:30,162 inlined from ‘_OutputIterator std::partial_sum(_InputIterator, _InputIterator, _OutputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; _OutputIterator = back_insert_iterator >]’ at /usr/include/c++/12/bits/stl_numeric.h:270:17, 2024-02-14T01:24:30,163 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-14T01:24:30,164 /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-14T01:24:30,164 1287 | _M_realloc_insert(end(), __x); 2024-02-14T01:24:30,165 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-14T01:24:30,165 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-02-14T01:24:30,166 inlined from ‘std::back_insert_iterator<_Container>& std::back_insert_iterator<_Container>::operator=(const typename _Container::value_type&) [with _Container = std::vector]’ at /usr/include/c++/12/bits/stl_iterator.h:735:22, 2024-02-14T01:24:30,167 inlined from ‘_OutputIterator std::partial_sum(_InputIterator, _InputIterator, _OutputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; _OutputIterator = back_insert_iterator >]’ at /usr/include/c++/12/bits/stl_numeric.h:274:16, 2024-02-14T01:24:30,168 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-02-14T01:24:30,169 /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator >’ changed in GCC 7.1 2024-02-14T01:24:30,169 1287 | _M_realloc_insert(end(), __x); 2024-02-14T01:24:30,170 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-02-14T01:24:30,302 [19/22] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllama.so -o vendor/llama.cpp/libllama.so vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o && : 2024-02-14T01:24:30,609 [20/22] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/common/libcommon.a && /usr/bin/ar qc vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o && /usr/bin/ranlib vendor/llama.cpp/common/libcommon.a && : 2024-02-14T01:24:30,676 [21/22] : && /usr/bin/c++ -fPIC -O3 -DNDEBUG -shared -Wl,-soname,libllava.so -o vendor/llama.cpp/examples/llava/libllava.so vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -Wl,-rpath,/tmp/tmp1ubcjt15/build/vendor/llama.cpp: vendor/llama.cpp/libllama.so && : 2024-02-14T01:24:30,924 [22/22] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/llava.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava.dir/clip.cpp.o vendor/llama.cpp/examples/llava/CMakeFiles/llava-cli.dir/llava-cli.cpp.o -o vendor/llama.cpp/examples/llava/llava-cli -Wl,-rpath,/tmp/tmp1ubcjt15/build/vendor/llama.cpp: vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.so && : 2024-02-14T01:24:30,928 *** Installing project into wheel... 2024-02-14T01:24:30,965 -- Install configuration: "Release" 2024-02-14T01:24:30,971 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/lib/libggml_shared.so 2024-02-14T01:24:31,019 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-02-14T01:24:31,021 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-02-14T01:24:31,025 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/include/ggml.h 2024-02-14T01:24:31,029 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/include/ggml-alloc.h 2024-02-14T01:24:31,031 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/include/ggml-backend.h 2024-02-14T01:24:31,034 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/lib/libllama.so 2024-02-14T01:24:31,107 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/include/llama.h 2024-02-14T01:24:31,112 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/bin/convert.py 2024-02-14T01:24:31,116 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/bin/convert-lora-to-ggml.py 2024-02-14T01:24:31,121 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/llama_core/libllama.so 2024-02-14T01:24:31,202 -- Installing: /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/llama_core/libllama.so 2024-02-14T01:24:31,296 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/lib/libllava.so 2024-02-14T01:24:31,316 -- Set runtime path of "/tmp/tmp1ubcjt15/wheel/platlib/lib/libllava.so" to "" 2024-02-14T01:24:31,356 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/bin/llava-cli 2024-02-14T01:24:31,368 -- Set runtime path of "/tmp/tmp1ubcjt15/wheel/platlib/bin/llava-cli" to "" 2024-02-14T01:24:31,395 -- Installing: /tmp/tmp1ubcjt15/wheel/platlib/llama_core/libllava.so 2024-02-14T01:24:31,416 -- Set runtime path of "/tmp/tmp1ubcjt15/wheel/platlib/llama_core/libllava.so" to "" 2024-02-14T01:24:31,458 -- Installing: /tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/llama_core/libllava.so 2024-02-14T01:24:31,479 -- Set runtime path of "/tmp/pip-wheel-l4yrl2zr/llama-core_69050e41587a4dc58d516e42fc1506fb/llama_core/libllava.so" to "" 2024-02-14T01:24:31,525 *** Making wheel... 2024-02-14T01:24:32,823 *** Created llama_core-0.0.7-cp311-cp311-manylinux_2_36_armv7l.whl... 2024-02-14T01:24:32,882 Building wheel for llama-core (pyproject.toml): finished with status 'done' 2024-02-14T01:24:32,910 Created wheel for llama-core: filename=llama_core-0.0.7-cp311-cp311-manylinux_2_36_armv7l.whl size=2356527 sha256=e048c0206b582812b9a23c7dee3ab719a30c783afb3c22d384dc7517e1837e89 2024-02-14T01:24:32,911 Stored in directory: /tmp/pip-ephem-wheel-cache-t1ze1wuv/wheels/b3/80/e9/adfd972ecf6d2c4c6f77d02b4a098882683bc568ade8dcbe21 2024-02-14T01:24:32,923 Successfully built llama-core 2024-02-14T01:24:32,984 Removed build tracker: '/tmp/pip-build-tracker-7nru3snc'