2024-05-20T08:37:15,827 Created temporary directory: /tmp/pip-build-tracker-53m3zib0 2024-05-20T08:37:15,828 Initialized build tracking at /tmp/pip-build-tracker-53m3zib0 2024-05-20T08:37:15,829 Created build tracker: /tmp/pip-build-tracker-53m3zib0 2024-05-20T08:37:15,829 Entered build tracker: /tmp/pip-build-tracker-53m3zib0 2024-05-20T08:37:15,830 Created temporary directory: /tmp/pip-wheel-iosc9fso 2024-05-20T08:37:15,833 Created temporary directory: /tmp/pip-ephem-wheel-cache-iwxtxbwp 2024-05-20T08:37:15,855 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-05-20T08:37:15,859 2 location(s) to search for versions of llama-cpp-conv: 2024-05-20T08:37:15,859 * https://pypi.org/simple/llama-cpp-conv/ 2024-05-20T08:37:15,859 * https://www.piwheels.org/simple/llama-cpp-conv/ 2024-05-20T08:37:15,859 Fetching project page and analyzing links: https://pypi.org/simple/llama-cpp-conv/ 2024-05-20T08:37:15,860 Getting page https://pypi.org/simple/llama-cpp-conv/ 2024-05-20T08:37:15,861 Found index url https://pypi.org/simple/ 2024-05-20T08:37:16,084 Fetched page https://pypi.org/simple/llama-cpp-conv/ as application/vnd.pypi.simple.v1+json 2024-05-20T08:37:16,097 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/6a/db/4944f6684c51fcd0d35e5c921facd6b92a983e615ca817aec0b8b0c94ffc/llama_cpp_conv-0.2.57-cp310-cp310-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,097 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/d7/cc/564d25d2901080b43b0d8e1c45f1cc56885094995f8f9db86e79ee47bb41/llama_cpp_conv-0.2.57-cp310-cp310-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,098 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/8f/df/f87f4d9c40d893cdee3f63b955d78509288954db0ea4c1783e7e6ec48e53/llama_cpp_conv-0.2.57-cp310-cp310-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,098 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/66/dd/b92b89e1a7fb9231907fda5373619fad83e3e593726457163e17a148952b/llama_cpp_conv-0.2.57-cp310-cp310-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,099 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/57/25/fca00deea19ee3e3ba6a577a47fe15360e20df2e7265be579480b4c29e09/llama_cpp_conv-0.2.57-cp310-cp310-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,100 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/4a/12/013261b42bbcda7c977eae75336b082196c11369c1f69e1d1cff60047a42/llama_cpp_conv-0.2.57-cp310-cp310-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,100 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/21/51/37d5fcd3317aae2124bf575f57a2775945cef99dd606e18d3bf019e16764/llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,101 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/40/89/3059ebaf400fe630ae8fc628f2b2d4d146a5a8b328b54ac74a99e1be5430/llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,102 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/bb/33/32be068bff0fa283f0646a99b5bb1812540aa142b323dc4f3179378ca2e2/llama_cpp_conv-0.2.57-cp311-cp311-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,102 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/2e/c7/ec440f3993a45cbc579107a1f2b4f8c61e0bab36ceedef2fd962b9ef25f7/llama_cpp_conv-0.2.57-cp311-cp311-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,103 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/ec/6d/c9713de408baa2a9410ce449c5308b7c5f2b5054d3ac5b5616d10e4a3a6d/llama_cpp_conv-0.2.57-cp311-cp311-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,104 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/31/fc/06cfa6ef71dc5e8683f23b681ccfd420b17616cd85e7c39fd304a65a4f8a/llama_cpp_conv-0.2.57-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,104 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/e2/7a/f5f1d56fc866dcfe547fb92d0111a998b7d53e9fbd412d6b6bb66c631906/llama_cpp_conv-0.2.57-cp38-cp38-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,105 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/06/a7/39dd6198298d8d27a454b30a4cb18a48f4a96e064c25fae2cc4c97ff771d/llama_cpp_conv-0.2.57-cp38-cp38-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,105 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/c6/b0/d1047e56e844d6e29d6839c24aaefabf576efad74c4932ab46435f9945f7/llama_cpp_conv-0.2.57-cp38-cp38-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,106 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/23/37/7b3f4e04e3fe0408e77eb3cec6a6ecdd5200da19f49334fe7e2ef30e3f28/llama_cpp_conv-0.2.57-cp38-cp38-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,106 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/94/fb/0dad5b4f320c25cd2c90e07476db75888ebfe958f1851d8a26337ac2271b/llama_cpp_conv-0.2.57-cp38-cp38-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,107 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/a5/f2/33063bcceb39fc5fb0fa436058afcd376fc3f7ee30018346108478daeff5/llama_cpp_conv-0.2.57-cp38-cp38-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,108 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/66/6e/63286e7a0c8158e5811f8c7000f81694c2c02d2b6a54f43b05cb30fdb649/llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,108 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/84/c8/359a8b2cdae109b4563b5993d9c560c3c45948e30ad5b83c7e0d674707df/llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,109 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/4d/0a/f514431e2cb8dc56378b17c131ca2d77d61dfa2169219f51589897475c64/llama_cpp_conv-0.2.57-cp39-cp39-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,110 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/08/f9/e981e918989ee556d1ff07b3508ac8ee59c10c8c21879b27ab5b01f36a99/llama_cpp_conv-0.2.57-cp39-cp39-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,110 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/74/d8/0b80732b9c0a37a36c326a5f694ad9d5a82048502638ef700fe5bc4ff4a4/llama_cpp_conv-0.2.57-cp39-cp39-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,111 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/d2/e4/714e08ceeb70d13eee9acae81cb1a150ba8dbc2dfe0188328f474aa63336/llama_cpp_conv-0.2.57-cp39-cp39-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,112 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/04/81/db6e3d121db9394160c3ed83c0f6c115a5e54415e0cd5bd807c46cd5fec9/llama_cpp_conv-0.2.57-pp38-pypy38_pp73-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,112 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/8c/e9/2e888f7b10cbf4625f5a0c76a0db8ba0d6af355193dddc91e45d18704bde/llama_cpp_conv-0.2.57-pp38-pypy38_pp73-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,113 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/27/11/21f92fd36ae7d2d38df0691c545f51fb0d3d747df5fc31291fa700741e5d/llama_cpp_conv-0.2.57-pp38-pypy38_pp73-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,113 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/be/c8/0fdc549df836ceeea6e8a9b7a8b2454052f4c6fa2c34fb0bab648ade7ed5/llama_cpp_conv-0.2.57-pp39-pypy39_pp73-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,114 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/c9/55/c738382bb1d2d45d107a70db456f8c26022cb1e9f729d757d6578a04b88c/llama_cpp_conv-0.2.57-pp39-pypy39_pp73-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,114 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/00/4e/3a809a80510c5f3f8032954ca330b02088a0ad7225d43c69edef100bd1e9/llama_cpp_conv-0.2.57-pp39-pypy39_pp73-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,115 Found link https://files.pythonhosted.org/packages/8d/d1/2a1b6cd2046cc322f8792af985a4b53acd8c47fa238db44fd1a6f21bd1f2/llama_cpp_conv-0.2.57.tar.gz (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8), version: 0.2.57 2024-05-20T08:37:16,116 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/b2/2b/4e12c57c053cce7ff1c23f33331038dc56d036e94f7d56a4ee83d7499fcd/llama_cpp_conv-0.2.58-cp310-cp310-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,117 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/e8/23/f992eeb566998a6fbc77e5aa045b4c2527b3951b620f29d807aca777aede/llama_cpp_conv-0.2.58-cp310-cp310-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,117 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/7b/74/4559c22198d50b5890ea892a72ea9a9b0970b5a6474f72d9233252cf3f2b/llama_cpp_conv-0.2.58-cp310-cp310-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,118 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/fc/d3/13716c0e84f5cd88d31be3d354760d7dfdd319d73c4fc6f86262fa3cbb7f/llama_cpp_conv-0.2.58-cp310-cp310-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,118 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/a1/0b/63b3113d3ce965781e00fe9299c0ed720b17bdc14d83c3f72ad60abd14e0/llama_cpp_conv-0.2.58-cp310-cp310-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,119 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/9a/4a/512abdbfdf7f20d953fe27a28a04be7bc29d274e5ca08148254c6dd75b65/llama_cpp_conv-0.2.58-cp310-cp310-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,120 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/20/af/d74a80edbccfe697a9427b10fe3f56ab50727bc7c48ec2cb8728cc865c59/llama_cpp_conv-0.2.58-cp311-cp311-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,120 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/25/5d/2f264c0da2778630862fd97833ae2ad216c1281e7957f754d0bf8d25b13f/llama_cpp_conv-0.2.58-cp311-cp311-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,121 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/a1/e2/8feb22cf659f5bb40e0756bdd6716bd558b13eecce3fed1bfe0155d471f5/llama_cpp_conv-0.2.58-cp311-cp311-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,121 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/e5/a7/7aa3000f8fe7d778e5299f6f07cfcd7cb03144c7a3e8c9c0989ee11bc60d/llama_cpp_conv-0.2.58-cp311-cp311-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,122 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/73/6b/c2e1527e051ba024adb526465fd565b657f68f15c2ed53274c1c0d39ccfa/llama_cpp_conv-0.2.58-cp311-cp311-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,122 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/16/34/20608dbe99bfc145ac6d23c9751a2080c70b086ee8fb0d3e4b196629e33e/llama_cpp_conv-0.2.58-cp311-cp311-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,123 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/f0/47/94dddc0c0c681b64d5cbc1899ab421a6985f6c3e374ed8fea9309e2115a0/llama_cpp_conv-0.2.58-cp38-cp38-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,123 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/a5/d8/d4925410137f175c6f5bcf82ad10464f1182a25d1cc481c2f52f9473837f/llama_cpp_conv-0.2.58-cp38-cp38-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,124 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/1c/79/d88f7649838a22ec606910c220431eccb9977f857a93c44bdc335006fb49/llama_cpp_conv-0.2.58-cp38-cp38-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,124 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/aa/0b/05ea892423b32b2b2b03ac70074d76577ebea6d86f4a9dc21fe91c52e4d9/llama_cpp_conv-0.2.58-cp38-cp38-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,125 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/f1/0e/8cb195a904c055210096fbdf0f1d1b6ddc1a45d19db827403d7d9fe59847/llama_cpp_conv-0.2.58-cp38-cp38-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,126 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/bd/ec/afc76da8a0efdc8221300cf445587a77dc90f6f3c28b29054c9037aa6954/llama_cpp_conv-0.2.58-cp38-cp38-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,126 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/0f/40/cb3adb561e4c28ae7ce3285af6f9c9b93afc5cc75841490dafc9dd354908/llama_cpp_conv-0.2.58-cp39-cp39-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,127 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/6c/b5/14e25114a437ce4adee60bd610d8ec08a6fa765c2569069732ac91d3a0bc/llama_cpp_conv-0.2.58-cp39-cp39-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,127 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/16/47/b9de87b44b7c3c1fcce6640c411339f30e4e54af6be0096c3a697f7e20d2/llama_cpp_conv-0.2.58-cp39-cp39-musllinux_1_1_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,128 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/ba/e6/8925f6b50bfab3a78ac5663574ad5bc9a0a86115392f8e309cce6ebd9e11/llama_cpp_conv-0.2.58-cp39-cp39-musllinux_1_1_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,128 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/2b/28/63fb5b15d0fab1ac96197066429678ba3adbba0b2e0801ddc101a44a81eb/llama_cpp_conv-0.2.58-cp39-cp39-win32.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,129 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/e1/70/65c182d9a38b0c1be59516b03c9591e7480b00b9adc6a9d66784e4fc2472/llama_cpp_conv-0.2.58-cp39-cp39-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,129 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/3b/0a/0da31efd1cd1f9ca29b88ecdf55c7185db93f5892e5ded380a2e3ada3a14/llama_cpp_conv-0.2.58-pp38-pypy38_pp73-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,130 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/81/09/31a12ce550a93cd11fc517faf240885fdaca416085a7dc0f7c010e2b90e0/llama_cpp_conv-0.2.58-pp38-pypy38_pp73-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,131 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/1b/d0/70eeabf3337e955d05b9a350529f3b10d28adac9c134b529e5c7a03884d2/llama_cpp_conv-0.2.58-pp38-pypy38_pp73-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,131 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/b9/86/538b423a55014d011f63d873a8a2f00a49563ec7fedd8d415071a892196f/llama_cpp_conv-0.2.58-pp39-pypy39_pp73-manylinux_2_17_i686.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,132 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/83/3e/13baae1cd753ef1202a55ef957714f7668280f8c0948d2f1ff30c617840e/llama_cpp_conv-0.2.58-pp39-pypy39_pp73-manylinux_2_17_x86_64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,132 Skipping link: No binaries permitted for llama-cpp-conv: https://files.pythonhosted.org/packages/b6/5f/a73a977fbd08905d5acb46681dcd4473e956ce0bb1a08ff9971e77ff2b2c/llama_cpp_conv-0.2.58-pp39-pypy39_pp73-win_amd64.whl (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,133 Found link https://files.pythonhosted.org/packages/4f/ca/521ff1d4d4216151d5955d7c0263fdd3c2f828d190dbc9e89108553674ff/llama_cpp_conv-0.2.58.tar.gz (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8), version: 0.2.58 2024-05-20T08:37:16,134 Found link https://files.pythonhosted.org/packages/09/c7/321e08076e312409de93d45738689fb33270f48a890daf2cd489c92454a8/llama_cpp_conv-0.2.68a1.tar.gz (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8), version: 0.2.68a1 2024-05-20T08:37:16,136 Found link https://files.pythonhosted.org/packages/34/c6/b7cfbf7a0417e3da8f43cd6a96e7e12d416d0a13a6a702852b5454df8379/llama_cpp_conv-0.2.68.tar.gz (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8), version: 0.2.68 2024-05-20T08:37:16,137 Found link https://files.pythonhosted.org/packages/df/66/f3b4a38a04b04edf9c70dac6a8160a1a0668bc96d7e8ae376e2cdbb4b4cb/llama_cpp_conv-0.2.75.tar.gz (from https://pypi.org/simple/llama-cpp-conv/) (requires-python:>=3.8), version: 0.2.75 2024-05-20T08:37:16,137 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-05-20T08:37:16,138 Getting page https://www.piwheels.org/simple/llama-cpp-conv/ 2024-05-20T08:37:16,139 Found index url https://www.piwheels.org/simple/ 2024-05-20T08:37:16,336 Fetched page https://www.piwheels.org/simple/llama-cpp-conv/ as text/html 2024-05-20T08:37:16,340 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.68-cp39-cp39-linux_armv6l.whl#sha256=596f65fdb0cdb73a909b57bec5fdb8322ef7286b5e36338ba183fb4ec77e6e04 (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,340 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.68-cp39-cp39-linux_armv7l.whl#sha256=596f65fdb0cdb73a909b57bec5fdb8322ef7286b5e36338ba183fb4ec77e6e04 (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,341 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.68a1-cp39-cp39-linux_armv6l.whl#sha256=dc6412c21c8174e57b167b113a616382b144c59ef5da13c6d6507d9a31d5f48c (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,341 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.68a1-cp39-cp39-linux_armv7l.whl#sha256=dc6412c21c8174e57b167b113a616382b144c59ef5da13c6d6507d9a31d5f48c (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,342 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.58-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=a504bddb2611e155118405ded0c673b0a619cc98f84d89e3ac487eb2a6ab2fa7 (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,343 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.58-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=40da2e97a7fedda33366f2426c8f782612de32096cea2919b15fca1a70b6e42e (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,343 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.57-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=c851c1100f9c04f112ebaaa0bb42bbc9ddbc7760a84e8d13e6610cddccde1912 (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,344 Skipping link: No binaries permitted for llama-cpp-conv: https://www.piwheels.org/simple/llama-cpp-conv/llama_cpp_conv-0.2.57-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=629119e6c3564b3c74f1a93dc42f951cf05dd112febfc51e364a791151e75eee (from https://www.piwheels.org/simple/llama-cpp-conv/) (requires-python:>=3.8) 2024-05-20T08:37:16,344 Skipping link: not a file: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-05-20T08:37:16,345 Skipping link: not a file: https://pypi.org/simple/llama-cpp-conv/ 2024-05-20T08:37:16,364 Given no hashes to check 1 links for project 'llama-cpp-conv': discarding no candidates 2024-05-20T08:37:16,382 Collecting llama-cpp-conv==0.2.75 2024-05-20T08:37:16,384 Created temporary directory: /tmp/pip-unpack-yg00v_rm 2024-05-20T08:37:16,604 Downloading llama_cpp_conv-0.2.75.tar.gz (51.3 MB) 2024-05-20T08:37:27,795 Added llama-cpp-conv==0.2.75 from https://files.pythonhosted.org/packages/df/66/f3b4a38a04b04edf9c70dac6a8160a1a0668bc96d7e8ae376e2cdbb4b4cb/llama_cpp_conv-0.2.75.tar.gz to build tracker '/tmp/pip-build-tracker-53m3zib0' 2024-05-20T08:37:27,800 Created temporary directory: /tmp/pip-build-env-mxkhdfrf 2024-05-20T08:37:27,805 Installing build dependencies: started 2024-05-20T08:37:27,806 Running command pip subprocess to install build dependencies 2024-05-20T08:37:28,953 Using pip 24.0 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11) 2024-05-20T08:37:29,460 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-05-20T08:37:29,914 Collecting scikit-build-core>=0.9.2 (from scikit-build-core[pyproject]>=0.9.2) 2024-05-20T08:37:29,934 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.9.4-py3-none-any.whl (151 kB) 2024-05-20T08:37:30,250 Collecting packaging>=21.3 (from scikit-build-core>=0.9.2->scikit-build-core[pyproject]>=0.9.2) 2024-05-20T08:37:30,267 Using cached https://www.piwheels.org/simple/packaging/packaging-24.0-py3-none-any.whl (53 kB) 2024-05-20T08:37:30,367 Collecting pathspec>=0.10.1 (from scikit-build-core>=0.9.2->scikit-build-core[pyproject]>=0.9.2) 2024-05-20T08:37:30,399 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-05-20T08:37:33,040 Installing collected packages: pathspec, packaging, scikit-build-core 2024-05-20T08:37:33,781 Successfully installed packaging-24.0 pathspec-0.12.1 scikit-build-core-0.9.4 2024-05-20T08:37:34,296 Installing build dependencies: finished with status 'done' 2024-05-20T08:37:34,300 Getting requirements to build wheel: started 2024-05-20T08:37:34,301 Running command Getting requirements to build wheel 2024-05-20T08:37:34,728 Getting requirements to build wheel: finished with status 'done' 2024-05-20T08:37:34,731 Created temporary directory: /tmp/pip-modern-metadata-uvzaak91 2024-05-20T08:37:34,734 Preparing metadata (pyproject.toml): started 2024-05-20T08:37:34,735 Running command Preparing metadata (pyproject.toml) 2024-05-20T08:37:35,250 *** scikit-build-core 0.9.4 using CMake 3.25.1 (metadata_wheel) 2024-05-20T08:37:35,345 Preparing metadata (pyproject.toml): finished with status 'done' 2024-05-20T08:37:35,352 Source in /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b has version 0.2.75, which satisfies requirement llama-cpp-conv==0.2.75 from https://files.pythonhosted.org/packages/df/66/f3b4a38a04b04edf9c70dac6a8160a1a0668bc96d7e8ae376e2cdbb4b4cb/llama_cpp_conv-0.2.75.tar.gz 2024-05-20T08:37:35,353 Removed llama-cpp-conv==0.2.75 from https://files.pythonhosted.org/packages/df/66/f3b4a38a04b04edf9c70dac6a8160a1a0668bc96d7e8ae376e2cdbb4b4cb/llama_cpp_conv-0.2.75.tar.gz from build tracker '/tmp/pip-build-tracker-53m3zib0' 2024-05-20T08:37:35,363 Created temporary directory: /tmp/pip-unpack-7e5x_f67 2024-05-20T08:37:35,364 Created temporary directory: /tmp/pip-unpack-04h2rl5m 2024-05-20T08:37:35,427 Building wheels for collected packages: llama-cpp-conv 2024-05-20T08:37:35,432 Created temporary directory: /tmp/pip-wheel-lbavehx1 2024-05-20T08:37:35,432 Destination directory: /tmp/pip-wheel-lbavehx1 2024-05-20T08:37:35,435 Building wheel for llama-cpp-conv (pyproject.toml): started 2024-05-20T08:37:35,436 Running command Building wheel for llama-cpp-conv (pyproject.toml) 2024-05-20T08:37:35,947 *** scikit-build-core 0.9.4 using CMake 3.25.1 (wheel) 2024-05-20T08:37:35,969 *** Configuring CMake... 2024-05-20T08:37:36,062 loading initial cache file /tmp/tmpru6a0l2b/build/CMakeInit.txt 2024-05-20T08:37:36,331 -- The C compiler identification is GNU 12.2.0 2024-05-20T08:37:36,628 -- The CXX compiler identification is GNU 12.2.0 2024-05-20T08:37:36,678 -- Detecting C compiler ABI info 2024-05-20T08:37:36,958 -- Detecting C compiler ABI info - done 2024-05-20T08:37:37,000 -- Check for working C compiler: /usr/bin/cc - skipped 2024-05-20T08:37:37,002 -- Detecting C compile features 2024-05-20T08:37:37,004 -- Detecting C compile features - done 2024-05-20T08:37:37,023 -- Detecting CXX compiler ABI info 2024-05-20T08:37:37,339 -- Detecting CXX compiler ABI info - done 2024-05-20T08:37:37,378 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-05-20T08:37:37,379 -- Detecting CXX compile features 2024-05-20T08:37:37,382 -- Detecting CXX compile features - done 2024-05-20T08:37:37,413 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-05-20T08:37:37,476 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-05-20T08:37:37,802 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-05-20T08:37:37,806 -- Found Threads: TRUE 2024-05-20T08:37:37,814 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-05-20T08:37:37,916 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-05-20T08:37:37,916 -- ARM detected 2024-05-20T08:37:37,919 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-05-20T08:37:38,239 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-05-20T08:37:38,280 CMake Warning (dev) at CMakeLists.txt:28 (install): 2024-05-20T08:37:38,281 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-05-20T08:37:38,281 This warning is for project developers. Use -Wno-dev to suppress it. 2024-05-20T08:37:38,282 CMake Warning (dev) at CMakeLists.txt:37 (install): 2024-05-20T08:37:38,283 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-05-20T08:37:38,283 This warning is for project developers. Use -Wno-dev to suppress it. 2024-05-20T08:37:38,285 -- Configuring done 2024-05-20T08:37:38,351 -- Generating done 2024-05-20T08:37:38,371 -- Build files have been written to: /tmp/tmpru6a0l2b/build 2024-05-20T08:37:38,382 *** Building project with Ninja... 2024-05-20T08:37:42,910 [1/24] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/ggml-alloc.c 2024-05-20T08:37:44,535 [2/24] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/ggml-backend.c 2024-05-20T08:37:56,227 [3/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/sgemm.cpp 2024-05-20T08:37:56,585 [4/24] cd /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/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-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-05-20T08:37:56,586 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-05-20T08:37:56,737 [5/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/build-info.cpp 2024-05-20T08:37:59,030 [6/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/unicode-data.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/unicode-data.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/unicode-data.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/unicode-data.cpp 2024-05-20T08:38:10,878 [7/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/sampling.cpp 2024-05-20T08:38:16,880 [8/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/console.cpp 2024-05-20T08:38:27,848 [9/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/grammar-parser.cpp 2024-05-20T08:38:47,019 [10/24] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/ggml-quants.c 2024-05-20T08:38:58,357 [11/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/unicode.cpp 2024-05-20T08:39:08,953 [12/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/train.cpp 2024-05-20T08:39:10,703 [13/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/ngram-cache.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/ngram-cache.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/ngram-cache.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/ngram-cache.cpp 2024-05-20T08:39:15,815 [14/24] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/ggml.c 2024-05-20T08:39:16,574 [15/24] : && /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 vendor/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && : 2024-05-20T08:39:23,051 [16/24] /usr/bin/c++ -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/../../common -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -MF vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o.d -o vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/quantize.cpp 2024-05-20T08:39:23,052 In file included from /usr/include/c++/12/vector:70, 2024-05-20T08:39:23,053 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/../../common/grammar-parser.h:14, 2024-05-20T08:39:23,054 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/../../common/sampling.h:5, 2024-05-20T08:39:23,055 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/../../common/common.h:7, 2024-05-20T08:39:23,056 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/quantize.cpp:1: 2024-05-20T08:39:23,057 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {llama_model_kv_override}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-05-20T08:39:23,058 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-05-20T08:39:23,059 439 | vector<_Tp, _Alloc>:: 2024-05-20T08:39:23,060 | ^~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:23,061 /usr/include/c++/12/bits/vector.tcc: In function ‘std::vector<_Tp, _Alloc>::reference std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {llama_model_kv_override}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-05-20T08:39:23,062 /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 2024-05-20T08:39:23,064 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-05-20T08:39:23,065 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:23,065 /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]’: 2024-05-20T08:39:23,066 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-05-20T08:39:23,067 439 | vector<_Tp, _Alloc>:: 2024-05-20T08:39:23,068 | ^~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:23,069 In member function ‘std::vector<_Tp, _Alloc>::reference std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-05-20T08:39:23,070 inlined from ‘int main(int, char**)’ at /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/quantize/quantize.cpp:341:34: 2024-05-20T08:39:23,071 /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 2024-05-20T08:39:23,072 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-05-20T08:39:23,073 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:27,313 [17/24] /usr/bin/c++ -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o -MF vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o.d -o vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/examples/imatrix/imatrix.cpp 2024-05-20T08:39:31,479 [18/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/common.cpp 2024-05-20T08:39:31,480 In file included from /usr/include/c++/12/vector:70, 2024-05-20T08:39:31,481 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/grammar-parser.h:14, 2024-05-20T08:39:31,482 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/sampling.h:5, 2024-05-20T08:39:31,483 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/common.h:7, 2024-05-20T08:39:31,483 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/common.cpp:1: 2024-05-20T08:39:31,484 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {llama_model_kv_override}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-05-20T08:39:31,486 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-05-20T08:39:31,487 439 | vector<_Tp, _Alloc>:: 2024-05-20T08:39:31,487 | ^~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:31,488 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {llama_model_kv_override}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-05-20T08:39:31,489 inlined from ‘bool parse_kv_override(const char*, std::vector&)’ at /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/common.cpp:280:27: 2024-05-20T08:39:31,489 /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 2024-05-20T08:39:31,490 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-05-20T08:39:31,491 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:31,492 /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]’: 2024-05-20T08:39:31,492 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-05-20T08:39:31,493 439 | vector<_Tp, _Alloc>:: 2024-05-20T08:39:31,494 | ^~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:31,494 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-05-20T08:39:31,495 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/common.cpp:1410:41: 2024-05-20T08:39:31,496 /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 2024-05-20T08:39:31,497 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-05-20T08:39:31,498 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:45,998 [19/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/. -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/json-schema-to-grammar.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/json-schema-to-grammar.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/json-schema-to-grammar.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/json-schema-to-grammar.cpp 2024-05-20T08:39:45,999 In file included from /usr/include/c++/12/vector:70, 2024-05-20T08:39:45,999 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/json.hpp:32, 2024-05-20T08:39:46,000 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/json-schema-to-grammar.h:6, 2024-05-20T08:39:46,001 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/json-schema-to-grammar.cpp:1: 2024-05-20T08:39:46,001 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const std::__cxx11::basic_string, std::allocator >&, const nlohmann::json_abi_v3_11_3::basic_json, std::allocator >, bool, long long int, long long unsigned int, double, std::allocator, nlohmann::json_abi_v3_11_3::adl_serializer, std::vector >, void>&}; _Tp = std::pair, nlohmann::json_abi_v3_11_3::basic_json >; _Alloc = std::allocator, nlohmann::json_abi_v3_11_3::basic_json > >]’: 2024-05-20T08:39:46,002 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector, nlohmann::json_abi_v3_11_3::basic_json > >::iterator’ changed in GCC 7.1 2024-05-20T08:39:46,002 439 | vector<_Tp, _Alloc>:: 2024-05-20T08:39:46,003 | ^~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:46,003 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {const std::__cxx11::basic_string, std::allocator >&, const nlohmann::json_abi_v3_11_3::basic_json, std::allocator >, bool, long long int, long long unsigned int, double, std::allocator, nlohmann::json_abi_v3_11_3::adl_serializer, std::vector >, void>&}; _Tp = std::pair, nlohmann::json_abi_v3_11_3::basic_json >; _Alloc = std::allocator, nlohmann::json_abi_v3_11_3::basic_json > >]’, 2024-05-20T08:39:46,003 inlined from ‘SchemaConverter::visit(const json&, const std::string&)::’ at /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/json-schema-to-grammar.cpp:676:48: 2024-05-20T08:39:46,004 /usr/include/c++/12/bits/vector.tcc:123:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator, nlohmann::json_abi_v3_11_3::basic_json >*, std::vector, nlohmann::json_abi_v3_11_3::basic_json > > >’ changed in GCC 7.1 2024-05-20T08:39:46,005 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-05-20T08:39:46,005 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:39:46,006 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {const std::__cxx11::basic_string, std::allocator >&, const nlohmann::json_abi_v3_11_3::basic_json, std::allocator >, bool, long long int, long long unsigned int, double, std::allocator, nlohmann::json_abi_v3_11_3::adl_serializer, std::vector >, void>&}; _Tp = std::pair, nlohmann::json_abi_v3_11_3::basic_json >; _Alloc = std::allocator, nlohmann::json_abi_v3_11_3::basic_json > >]’, 2024-05-20T08:39:46,006 inlined from ‘std::string SchemaConverter::visit(const json&, const std::string&)’ at /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/common/json-schema-to-grammar.cpp:660:44: 2024-05-20T08:39:46,007 /usr/include/c++/12/bits/vector.tcc:123:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator, nlohmann::json_abi_v3_11_3::basic_json >*, std::vector, nlohmann::json_abi_v3_11_3::basic_json > > >’ changed in GCC 7.1 2024-05-20T08:39:46,008 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-05-20T08:39:46,008 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,016 [20/24] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -DGGML_USE_LLAMAFILE -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/. -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp 2024-05-20T08:40:44,017 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp: In function ‘float* llama_get_logits_ith(llama_context*, int32_t)’: 2024-05-20T08:40:44,018 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:17525:65: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector::size_type’ {aka ‘unsigned int’} [-Wformat=] 2024-05-20T08:40:44,018 17525 | throw std::runtime_error(format("out of range [0, %lu)", ctx->output_ids.size())); 2024-05-20T08:40:44,019 | ~~^ ~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,019 | | | 2024-05-20T08:40:44,020 | long unsigned int std::vector::size_type {aka unsigned int} 2024-05-20T08:40:44,020 | %u 2024-05-20T08:40:44,021 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp: In function ‘float* llama_get_embeddings_ith(llama_context*, int32_t)’: 2024-05-20T08:40:44,021 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:17570:65: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector::size_type’ {aka ‘unsigned int’} [-Wformat=] 2024-05-20T08:40:44,022 17570 | throw std::runtime_error(format("out of range [0, %lu)", ctx->output_ids.size())); 2024-05-20T08:40:44,022 | ~~^ ~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,023 | | | 2024-05-20T08:40:44,023 | long unsigned int std::vector::size_type {aka unsigned int} 2024-05-20T08:40:44,024 | %u 2024-05-20T08:40:44,025 In file included from /usr/include/c++/12/vector:64, 2024-05-20T08:40:44,025 from /usr/include/c++/12/bits/random.h:34, 2024-05-20T08:40:44,026 from /usr/include/c++/12/random:49, 2024-05-20T08:40:44,026 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.h:1107, 2024-05-20T08:40:44,026 from /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:2: 2024-05-20T08:40:44,027 /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]’: 2024-05-20T08:40:44,027 /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 2024-05-20T08:40:44,027 673 | vector(initializer_list __l, 2024-05-20T08:40:44,028 | ^~~~~~ 2024-05-20T08:40:44,028 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/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*)’: 2024-05-20T08:40:44,029 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4939:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,029 4939 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,030 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,030 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4943:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,031 4943 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,031 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,032 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4945:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,033 4945 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,033 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,034 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4948:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,034 4948 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,035 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,035 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4964:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,036 4964 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,037 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,037 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4966:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,037 4966 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,038 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,038 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4969:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,038 4969 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}, false); 2024-05-20T08:40:44,039 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,039 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4970:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,040 4970 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}, false); 2024-05-20T08:40:44,040 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,040 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4971:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,041 4971 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}, false); 2024-05-20T08:40:44,041 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,042 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4972:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,043 4972 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, false); 2024-05-20T08:40:44,043 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,044 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4974:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,044 4974 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,045 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,045 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4977:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,046 4977 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,046 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,047 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4978:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,047 4978 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,048 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,048 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4979:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,049 4979 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,049 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,049 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4981:66: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,050 4981 | layer.ffn_gate_inp = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}); 2024-05-20T08:40:44,050 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,051 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4983:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,051 4983 | layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff, n_expert}, false); 2024-05-20T08:40:44,052 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,052 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4985:71: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,053 4985 | layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), { n_ff, n_embd, n_expert}); 2024-05-20T08:40:44,053 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,054 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:4986:71: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,054 4986 | layer.ffn_up_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff, n_expert}); 2024-05-20T08:40:44,055 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,055 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5006:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,056 5006 | ml.create_tensor_as_view(ctx_split, layer.ffn_gate_exps, tn(LLM_TENSOR_FFN_GATE_EXP, "weight", i, x), { n_embd, n_ff }, layer.ffn_gate_exps->nb[2]*x); 2024-05-20T08:40:44,056 | ~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,057 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5007:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,057 5007 | ml.create_tensor_as_view(ctx_split, layer.ffn_down_exps, tn(LLM_TENSOR_FFN_DOWN_EXP, "weight", i, x), { n_ff, n_embd }, layer.ffn_down_exps->nb[2]*x); 2024-05-20T08:40:44,058 | ~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,058 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5008:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,058 5008 | ml.create_tensor_as_view(ctx_split, layer.ffn_up_exps, tn(LLM_TENSOR_FFN_UP_EXP, "weight", i, x), { n_embd, n_ff }, layer.ffn_up_exps->nb[2]*x); 2024-05-20T08:40:44,059 | ~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,059 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5020:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,059 5020 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,060 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,061 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5024:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,061 5024 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,062 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,062 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5025:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,063 5025 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,063 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,064 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5028:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,064 5028 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,065 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,066 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5040:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,066 5040 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,067 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,067 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5042:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,068 5042 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,068 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,069 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5043:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,069 5043 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,069 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,070 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5044:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,070 5044 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,071 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,071 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5045:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,071 5045 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,072 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,073 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5047:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,073 5047 | layer.attn_out_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,074 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,075 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5051:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,075 5051 | layer.ffn_gate_inp = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}); 2024-05-20T08:40:44,076 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,076 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5053:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,077 5053 | layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff, n_expert}, false); 2024-05-20T08:40:44,077 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,078 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5055:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,078 5055 | layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), { n_ff, n_embd, n_expert}); 2024-05-20T08:40:44,079 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,079 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5056:67: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,079 5056 | layer.ffn_up_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff, n_expert}); 2024-05-20T08:40:44,080 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,080 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5082:66: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,081 5082 | layer.layer_out_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_LAYER_OUT_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,081 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,082 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5091:50: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,082 5091 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,082 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,083 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5095:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,084 5095 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,084 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,085 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5096:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,085 5096 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,086 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,086 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5105:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,087 5105 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,087 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,088 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5108:50: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,089 5108 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,089 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,089 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5110:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,090 5110 | layer.attn_out_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,090 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,090 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5112:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,091 5112 | layer.ffn_gate_inp = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}); 2024-05-20T08:40:44,091 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,092 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5113:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,092 5113 | layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff, n_expert}); 2024-05-20T08:40:44,093 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,093 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5114:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,094 5114 | layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff, n_embd, n_expert}); 2024-05-20T08:40:44,094 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,095 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5120:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,096 5120 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,096 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,097 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5122:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,097 5122 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,098 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,098 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5123:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,099 5123 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,100 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,101 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5134:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,101 5134 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,102 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,102 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5136:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,103 5136 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,103 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,104 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5137:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,104 5137 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,105 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,106 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5142:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,107 5142 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,107 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,108 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5148:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,108 5148 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,109 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,109 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5152:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,110 5152 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,110 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,111 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5153:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,111 5153 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,112 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,113 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5155:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,113 5155 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,113 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,114 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5157:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,114 5157 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-05-20T08:40:44,115 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,115 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5178:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,115 5178 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,116 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,117 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5184:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,117 5184 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,118 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,118 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5185:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,119 5185 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-05-20T08:40:44,120 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,120 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5189:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,121 5189 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,121 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,122 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5190:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,122 5190 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,123 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,124 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5191:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,124 5191 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,124 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,125 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5203:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,125 5203 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-05-20T08:40:44,126 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,126 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5207:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,126 5207 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-05-20T08:40:44,127 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,127 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5221:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,128 5221 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,129 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,129 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5224:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,130 5224 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,130 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,131 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5225:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,131 5225 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,132 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,132 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5226:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,133 5226 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,133 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,134 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5263:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,134 5263 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,135 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,135 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5264:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,136 5264 | model.type_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_vocab_type}); 2024-05-20T08:40:44,136 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,136 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5266:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,137 5266 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-05-20T08:40:44,137 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,138 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5269:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,138 5269 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,139 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,139 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5270:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,140 5270 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,141 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,141 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5279:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,142 5279 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,142 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,143 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5280:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,143 5280 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-05-20T08:40:44,144 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,144 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5282:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,145 5282 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,146 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,146 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5283:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,146 5283 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,147 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,147 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5285:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,147 5285 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,148 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,148 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5286:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,149 5286 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,149 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,150 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5288:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,150 5288 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-05-20T08:40:44,151 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,151 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5300:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,152 5300 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-05-20T08:40:44,152 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,153 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5301:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,153 5301 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-05-20T08:40:44,154 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,154 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5303:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,155 5303 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-05-20T08:40:44,156 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,156 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5305:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,157 5305 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,157 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,157 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5314:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,158 5314 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // word_embeddings 2024-05-20T08:40:44,158 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,159 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5315:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,159 5315 | model.type_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_vocab_type}); //token_type_embeddings 2024-05-20T08:40:44,160 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,160 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5316:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,161 5316 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); // LayerNorm 2024-05-20T08:40:44,161 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,162 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5317:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,163 5317 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); //LayerNorm bias 2024-05-20T08:40:44,163 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,164 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5337:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,164 5337 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,165 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,165 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5338:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,166 5338 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,167 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,167 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5346:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,167 5346 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,168 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,169 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5358:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,169 5358 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,170 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,171 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5359:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,171 5359 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,172 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,172 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5360:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,173 5360 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,173 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,174 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5364:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,175 5364 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,175 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,176 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5365:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,176 5365 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,177 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,177 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5366:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,178 5366 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,179 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,179 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5396:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,180 5396 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,180 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,181 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5397:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,181 5397 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}, false); 2024-05-20T08:40:44,182 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,182 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5401:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,183 5401 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,183 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,184 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5402:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,184 5402 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, false); 2024-05-20T08:40:44,185 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,186 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5404:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,186 5404 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,187 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,187 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5406:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,188 5406 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-05-20T08:40:44,189 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,189 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5448:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,190 5448 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,191 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,191 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5452:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,192 5452 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,193 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,193 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5453:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,194 5453 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,194 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,195 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5454:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,196 5454 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,196 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,197 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5486:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,197 5486 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,198 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,199 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5491:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,200 5491 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,200 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,201 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5495:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,202 5495 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,202 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,203 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5496:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,203 5496 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,204 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,205 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5515:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,206 5515 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff/2}); 2024-05-20T08:40:44,207 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,207 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5520:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,208 5520 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,208 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,209 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5524:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,209 5524 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,210 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,210 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5525:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,211 5525 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,212 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,213 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5528:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,214 5528 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,215 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,216 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5540:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,217 5540 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,218 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,219 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5544:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,220 5544 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,220 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,221 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5545:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,222 5545 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,223 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,224 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5549:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,225 5549 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,226 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,226 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5561:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,227 5561 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,228 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,228 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5565:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,229 5565 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,230 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,231 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5566:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,231 5566 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,232 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,232 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5609:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,233 5609 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,234 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,234 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5613:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,235 5613 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,235 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,236 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5614:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,236 5614 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,237 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,238 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5615:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,238 5615 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,239 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,239 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5616:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,240 5616 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-05-20T08:40:44,240 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,241 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5632:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,241 5632 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,242 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,242 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5633:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,243 5633 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-05-20T08:40:44,243 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,244 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5635:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,244 5635 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,245 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,245 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5636:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,246 5636 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,246 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,247 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5638:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,248 5638 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,248 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,249 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5639:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,250 5639 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,250 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,251 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5645:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,251 5645 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-05-20T08:40:44,252 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,252 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5648:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,253 5648 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,253 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,254 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5654:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,254 5654 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }); 2024-05-20T08:40:44,255 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,256 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5658:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,257 5658 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }); 2024-05-20T08:40:44,257 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,258 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5659:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,259 5659 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), { n_embd, n_vocab }); 2024-05-20T08:40:44,260 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,261 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5671:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,261 5671 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), { n_embd, n_embd }); 2024-05-20T08:40:44,262 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,263 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5676:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,264 5676 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), { n_embd, 2 * n_ff }); 2024-05-20T08:40:44,265 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,265 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5681:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,266 5681 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,266 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,267 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5685:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,268 5685 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,268 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,269 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5686:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,269 5686 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,270 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,271 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5698:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,272 5698 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,273 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,273 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5699:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,274 5699 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,275 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,276 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5709:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,276 5709 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,277 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,278 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5710:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,279 5710 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-05-20T08:40:44,279 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,280 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5714:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,281 5714 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,281 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,282 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5715:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,282 5715 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,283 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,283 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5716:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,284 5716 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,284 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,285 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5735:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,286 5735 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-05-20T08:40:44,287 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,287 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5740:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,288 5740 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,289 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,289 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5746:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,290 5746 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,291 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,291 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5750:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,292 5750 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,293 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,293 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5751:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,294 5751 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,295 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,295 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5752:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,296 5752 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,297 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,297 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5765:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,298 5765 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-05-20T08:40:44,298 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,299 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5774:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,300 5774 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-05-20T08:40:44,300 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,301 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5776:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,302 5776 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,302 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,303 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5782:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,303 5782 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,304 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,305 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5784:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,305 5784 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,306 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,307 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5785:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,307 5785 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,308 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,309 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5786:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,309 5786 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,310 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,310 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5794:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,311 5794 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,311 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,312 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5797:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,313 5797 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,314 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,314 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5799:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,315 5799 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,315 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,316 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5803:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,317 5803 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-05-20T08:40:44,317 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,318 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5806:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,319 5806 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,319 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,320 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5807:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,320 5807 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,322 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,322 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5812:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,323 5812 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,323 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,324 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5816:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,324 5816 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,324 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,325 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5817:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,325 5817 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,326 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,327 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5829:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,327 5829 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,328 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,329 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5832:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,330 5832 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,330 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,331 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5836:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,332 5836 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,332 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,333 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5841:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,334 5841 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,334 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,335 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5844:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,336 5844 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,336 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,337 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5845:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,338 5845 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // same as tok_embd, duplicated to allow offloading 2024-05-20T08:40:44,338 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,339 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5862:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,339 5862 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd_head_k * hparams.n_head}); 2024-05-20T08:40:44,340 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,341 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5868:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,341 5868 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,342 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,343 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5869:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,343 5869 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,344 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,345 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5875:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,345 5875 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,346 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,346 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5879:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,347 5879 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,348 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,348 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5880:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,349 5880 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-05-20T08:40:44,350 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,350 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5882:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,351 5882 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,351 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,352 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5885:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,352 5885 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,352 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,353 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5899:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,353 5899 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-05-20T08:40:44,354 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,355 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5908:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,355 5908 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,356 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,360 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5909:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,362 5909 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-05-20T08:40:44,367 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,381 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5913:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,386 5913 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-05-20T08:40:44,386 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,387 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5915:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,388 5915 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,395 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,395 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5932:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,396 5932 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,396 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,397 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5936:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,397 5936 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,398 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,402 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5938:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,417 5938 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,434 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,435 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5941:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,436 5941 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,436 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,437 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5954:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,438 5954 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,439 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,439 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5956:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,440 5956 | layer.ssm_in = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, 2*d_inner}); 2024-05-20T08:40:44,440 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,441 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5958:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,442 5958 | layer.ssm_conv1d = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner}); 2024-05-20T08:40:44,443 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,444 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5959:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,444 5959 | layer.ssm_conv1d_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner}); 2024-05-20T08:40:44,444 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,445 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5961:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,445 5961 | layer.ssm_x = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_X, "weight", i), {d_inner, dt_rank + 2*d_state}); 2024-05-20T08:40:44,446 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,446 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5963:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,447 5963 | layer.ssm_dt = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_DT, "weight", i), {dt_rank, d_inner}); 2024-05-20T08:40:44,447 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,448 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5964:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,448 5964 | layer.ssm_dt_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_DT, "bias", i), {d_inner}); 2024-05-20T08:40:44,449 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,450 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5967:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,450 5967 | layer.ssm_a = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_A, i), {d_state, d_inner}); 2024-05-20T08:40:44,451 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,451 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5968:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,452 5968 | layer.ssm_d = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_D, i), {d_inner}); 2024-05-20T08:40:44,452 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,453 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5971:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,454 5971 | layer.ssm_out = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}); 2024-05-20T08:40:44,454 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,455 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5976:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,455 5976 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,456 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,457 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5978:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,457 5978 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,458 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,458 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5979:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,459 5979 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,459 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,460 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5986:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,460 5986 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,461 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,461 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5987:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,462 5987 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,462 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,463 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5988:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,463 5988 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-05-20T08:40:44,464 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,465 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5990:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,465 5990 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-05-20T08:40:44,466 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,466 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5991:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,467 5991 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-05-20T08:40:44,468 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,468 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5992:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,469 5992 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,469 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,470 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:5998:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,470 5998 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,470 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,471 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6002:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,471 6002 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-05-20T08:40:44,472 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,473 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6004:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,473 6004 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,474 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,474 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6018:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,475 6018 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {hparams.n_embd_head_k, hparams.n_head}); 2024-05-20T08:40:44,476 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,476 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6019:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,477 6019 | layer.attn_k_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {hparams.n_embd_head_k, hparams.n_head_kv}); 2024-05-20T08:40:44,477 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,478 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6022:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,479 6022 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-05-20T08:40:44,479 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,480 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6028:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,481 6028 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,481 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,482 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6034:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,482 6034 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,483 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,483 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6038:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,484 6038 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-05-20T08:40:44,484 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,485 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6041:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,486 6041 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-05-20T08:40:44,486 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,487 /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/vendor/llama.cpp/llama.cpp:6059:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-05-20T08:40:44,488 6059 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-05-20T08:40:44,489 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,489 In file included from /usr/include/c++/12/vector:70: 2024-05-20T08:40:44,490 /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]’: 2024-05-20T08:40:44,491 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-05-20T08:40:44,491 439 | vector<_Tp, _Alloc>:: 2024-05-20T08:40:44,492 | ^~~~~~~~~~~~~~~~~~~ 2024-05-20T08:40:44,493 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-05-20T08:40:44,494 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, 2024-05-20T08:40:44,494 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, 2024-05-20T08:40:44,495 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-05-20T08:40:44,496 /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 2024-05-20T08:40:44,496 1287 | _M_realloc_insert(end(), __x); 2024-05-20T08:40:44,497 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-05-20T08:40:44,497 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-05-20T08:40:44,498 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, 2024-05-20T08:40:44,498 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, 2024-05-20T08:40:44,499 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-05-20T08:40:44,499 /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 2024-05-20T08:40:44,500 1287 | _M_realloc_insert(end(), __x); 2024-05-20T08:40:44,500 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-05-20T08:40:44,689 [21/24] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/libllama.a && /usr/bin/ar qc vendor/llama.cpp/libllama.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/sgemm.cpp.o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o vendor/llama.cpp/CMakeFiles/llama.dir/unicode-data.cpp.o && /usr/bin/ranlib vendor/llama.cpp/libllama.a && : 2024-05-20T08:40:45,042 [22/24] : && /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/json-schema-to-grammar.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/ngram-cache.cpp.o && /usr/bin/ranlib vendor/llama.cpp/common/libcommon.a && : 2024-05-20T08:40:45,648 [23/24] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -o vendor/llama.cpp/examples/quantize/quantize vendor/llama.cpp/libllama.a vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.a && : 2024-05-20T08:40:45,652 [24/24] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/examples/imatrix/CMakeFiles/imatrix.dir/imatrix.cpp.o -o vendor/llama.cpp/examples/imatrix/imatrix vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/libllama.a && : 2024-05-20T08:40:45,657 *** Installing project into wheel... 2024-05-20T08:40:45,693 -- Install configuration: "Release" 2024-05-20T08:40:45,697 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-05-20T08:40:45,700 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-05-20T08:40:45,703 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/include/ggml.h 2024-05-20T08:40:45,708 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/include/ggml-alloc.h 2024-05-20T08:40:45,710 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/include/ggml-backend.h 2024-05-20T08:40:45,713 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/lib/libllama.a 2024-05-20T08:40:45,760 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/include/llama.h 2024-05-20T08:40:45,765 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/bin/convert.py 2024-05-20T08:40:45,772 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/bin/quantize 2024-05-20T08:40:45,896 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/bin/imatrix 2024-05-20T08:40:46,028 -- Installing: /tmp/tmpru6a0l2b/wheel/platlib/llama_cpp/libllama.a 2024-05-20T08:40:46,072 -- Installing: /tmp/pip-wheel-iosc9fso/llama-cpp-conv_5b5da9614984497a8987ae19913c181b/llama_cpp/libllama.a 2024-05-20T08:40:46,124 *** Making wheel... 2024-05-20T08:40:48,459 *** Created llama_cpp_conv-0.2.75-cp311-cp311-linux_armv7l.whl... 2024-05-20T08:40:48,518 Building wheel for llama-cpp-conv (pyproject.toml): finished with status 'done' 2024-05-20T08:40:48,562 Created wheel for llama-cpp-conv: filename=llama_cpp_conv-0.2.75-cp311-cp311-linux_armv7l.whl size=3937198 sha256=dece95a90e7a64536f7342dfd8b71e8978b64a0df3da9f7c365087d70ed0562e 2024-05-20T08:40:48,563 Stored in directory: /tmp/pip-ephem-wheel-cache-iwxtxbwp/wheels/45/f3/f8/653e29274034aad498bf7d7bee315338582d414dd1d6ee8c82 2024-05-20T08:40:48,581 Successfully built llama-cpp-conv 2024-05-20T08:40:48,673 Removed build tracker: '/tmp/pip-build-tracker-53m3zib0'