2024-04-01T07:27:49,227 Created temporary directory: /tmp/pip-build-tracker-rqnice_z 2024-04-01T07:27:49,228 Initialized build tracking at /tmp/pip-build-tracker-rqnice_z 2024-04-01T07:27:49,228 Created build tracker: /tmp/pip-build-tracker-rqnice_z 2024-04-01T07:27:49,229 Entered build tracker: /tmp/pip-build-tracker-rqnice_z 2024-04-01T07:27:49,230 Created temporary directory: /tmp/pip-wheel-81m8m71x 2024-04-01T07:27:49,233 Created temporary directory: /tmp/pip-ephem-wheel-cache-bj0ha7nk 2024-04-01T07:27:49,259 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-04-01T07:27:49,263 2 location(s) to search for versions of llama-cpp-conv: 2024-04-01T07:27:49,263 * https://pypi.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,263 * https://www.piwheels.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,263 Fetching project page and analyzing links: https://pypi.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,264 Getting page https://pypi.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,266 Found index url https://pypi.org/simple/ 2024-04-01T07:27:49,482 Fetched page https://pypi.org/simple/llama-cpp-conv/ as application/vnd.pypi.simple.v1+json 2024-04-01T07:27:49,494 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) 2024-04-01T07:27:49,495 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) 2024-04-01T07:27:49,495 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) 2024-04-01T07:27:49,496 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) 2024-04-01T07:27:49,497 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) 2024-04-01T07:27:49,497 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) 2024-04-01T07:27:49,498 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) 2024-04-01T07:27:49,499 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) 2024-04-01T07:27:49,499 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) 2024-04-01T07:27:49,500 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) 2024-04-01T07:27:49,501 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) 2024-04-01T07:27:49,502 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) 2024-04-01T07:27:49,502 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) 2024-04-01T07:27:49,503 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) 2024-04-01T07:27:49,503 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) 2024-04-01T07:27:49,504 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) 2024-04-01T07:27:49,504 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) 2024-04-01T07:27:49,505 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) 2024-04-01T07:27:49,505 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) 2024-04-01T07:27:49,506 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) 2024-04-01T07:27:49,507 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) 2024-04-01T07:27:49,507 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) 2024-04-01T07:27:49,508 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) 2024-04-01T07:27:49,508 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) 2024-04-01T07:27:49,509 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) 2024-04-01T07:27:49,510 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) 2024-04-01T07:27:49,510 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) 2024-04-01T07:27:49,511 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) 2024-04-01T07:27:49,511 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) 2024-04-01T07:27:49,512 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) 2024-04-01T07:27:49,513 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 2024-04-01T07:27:49,513 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) 2024-04-01T07:27:49,514 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) 2024-04-01T07:27:49,515 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) 2024-04-01T07:27:49,515 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) 2024-04-01T07:27:49,516 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) 2024-04-01T07:27:49,516 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) 2024-04-01T07:27:49,517 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) 2024-04-01T07:27:49,518 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) 2024-04-01T07:27:49,518 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) 2024-04-01T07:27:49,519 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) 2024-04-01T07:27:49,519 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) 2024-04-01T07:27:49,520 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) 2024-04-01T07:27:49,520 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) 2024-04-01T07:27:49,521 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) 2024-04-01T07:27:49,521 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) 2024-04-01T07:27:49,522 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) 2024-04-01T07:27:49,522 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) 2024-04-01T07:27:49,523 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) 2024-04-01T07:27:49,524 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) 2024-04-01T07:27:49,524 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) 2024-04-01T07:27:49,525 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) 2024-04-01T07:27:49,525 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) 2024-04-01T07:27:49,526 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) 2024-04-01T07:27:49,526 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) 2024-04-01T07:27:49,527 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) 2024-04-01T07:27:49,527 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) 2024-04-01T07:27:49,528 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) 2024-04-01T07:27:49,528 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) 2024-04-01T07:27:49,529 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) 2024-04-01T07:27:49,529 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) 2024-04-01T07:27:49,530 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 2024-04-01T07:27:49,531 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,532 Getting page https://www.piwheels.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,533 Found index url https://www.piwheels.org/simple/ 2024-04-01T07:27:49,707 Fetched page https://www.piwheels.org/simple/llama-cpp-conv/ as text/html 2024-04-01T07:27:49,709 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) 2024-04-01T07:27:49,710 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) 2024-04-01T07:27:49,711 Skipping link: not a file: https://www.piwheels.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,711 Skipping link: not a file: https://pypi.org/simple/llama-cpp-conv/ 2024-04-01T07:27:49,731 Given no hashes to check 1 links for project 'llama-cpp-conv': discarding no candidates 2024-04-01T07:27:49,748 Collecting llama-cpp-conv==0.2.58 2024-04-01T07:27:49,751 Created temporary directory: /tmp/pip-unpack-5e1z6qp0 2024-04-01T07:27:50,214 Downloading llama_cpp_conv-0.2.58.tar.gz (38.1 MB) 2024-04-01T07:27:59,071 Added llama-cpp-conv==0.2.58 from https://files.pythonhosted.org/packages/4f/ca/521ff1d4d4216151d5955d7c0263fdd3c2f828d190dbc9e89108553674ff/llama_cpp_conv-0.2.58.tar.gz to build tracker '/tmp/pip-build-tracker-rqnice_z' 2024-04-01T07:27:59,076 Created temporary directory: /tmp/pip-build-env-ki6gny9k 2024-04-01T07:27:59,080 Installing build dependencies: started 2024-04-01T07:27:59,082 Running command pip subprocess to install build dependencies 2024-04-01T07:28:00,209 Using pip 24.0 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11) 2024-04-01T07:28:00,701 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2024-04-01T07:28:01,551 Collecting scikit-build-core>=0.5.1 (from scikit-build-core[pyproject]>=0.5.1) 2024-04-01T07:28:01,742 Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.2-py3-none-any.whl (140 kB) 2024-04-01T07:28:02,224 Collecting packaging>=20.9 (from scikit-build-core>=0.5.1->scikit-build-core[pyproject]>=0.5.1) 2024-04-01T07:28:02,294 Using cached https://www.piwheels.org/simple/packaging/packaging-24.0-py3-none-any.whl (53 kB) 2024-04-01T07:28:02,697 Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]>=0.5.1) 2024-04-01T07:28:02,715 Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB) 2024-04-01T07:28:02,796 Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]>=0.5.1) 2024-04-01T07:28:02,812 Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB) 2024-04-01T07:28:05,348 Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata 2024-04-01T07:28:06,037 Successfully installed packaging-24.0 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.2 2024-04-01T07:28:06,495 Installing build dependencies: finished with status 'done' 2024-04-01T07:28:06,499 Getting requirements to build wheel: started 2024-04-01T07:28:06,500 Running command Getting requirements to build wheel 2024-04-01T07:28:07,154 Getting requirements to build wheel: finished with status 'done' 2024-04-01T07:28:07,187 Created temporary directory: /tmp/pip-modern-metadata-on7eblq_ 2024-04-01T07:28:07,189 Preparing metadata (pyproject.toml): started 2024-04-01T07:28:07,191 Running command Preparing metadata (pyproject.toml) 2024-04-01T07:28:07,730 *** scikit-build-core 0.8.2 using CMake 3.25.1 (metadata_wheel) 2024-04-01T07:28:07,823 Preparing metadata (pyproject.toml): finished with status 'done' 2024-04-01T07:28:07,828 Source in /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77 has version 0.2.58, which satisfies requirement llama-cpp-conv==0.2.58 from https://files.pythonhosted.org/packages/4f/ca/521ff1d4d4216151d5955d7c0263fdd3c2f828d190dbc9e89108553674ff/llama_cpp_conv-0.2.58.tar.gz 2024-04-01T07:28:07,828 Removed llama-cpp-conv==0.2.58 from https://files.pythonhosted.org/packages/4f/ca/521ff1d4d4216151d5955d7c0263fdd3c2f828d190dbc9e89108553674ff/llama_cpp_conv-0.2.58.tar.gz from build tracker '/tmp/pip-build-tracker-rqnice_z' 2024-04-01T07:28:07,834 Created temporary directory: /tmp/pip-unpack-31dpuurs 2024-04-01T07:28:07,835 Created temporary directory: /tmp/pip-unpack-efa90ukm 2024-04-01T07:28:07,889 Building wheels for collected packages: llama-cpp-conv 2024-04-01T07:28:07,893 Created temporary directory: /tmp/pip-wheel-6g_yse67 2024-04-01T07:28:07,894 Destination directory: /tmp/pip-wheel-6g_yse67 2024-04-01T07:28:07,896 Building wheel for llama-cpp-conv (pyproject.toml): started 2024-04-01T07:28:07,897 Running command Building wheel for llama-cpp-conv (pyproject.toml) 2024-04-01T07:28:08,385 *** scikit-build-core 0.8.2 using CMake 3.25.1 (wheel) 2024-04-01T07:28:08,404 *** Configuring CMake... 2024-04-01T07:28:08,494 loading initial cache file /tmp/tmp9yvzfglc/build/CMakeInit.txt 2024-04-01T07:28:08,825 -- The C compiler identification is GNU 12.2.0 2024-04-01T07:28:09,161 -- The CXX compiler identification is GNU 12.2.0 2024-04-01T07:28:09,225 -- Detecting C compiler ABI info 2024-04-01T07:28:09,520 -- Detecting C compiler ABI info - done 2024-04-01T07:28:09,560 -- Check for working C compiler: /usr/bin/cc - skipped 2024-04-01T07:28:09,570 -- Detecting C compile features 2024-04-01T07:28:09,579 -- Detecting C compile features - done 2024-04-01T07:28:09,602 -- Detecting CXX compiler ABI info 2024-04-01T07:28:09,916 -- Detecting CXX compiler ABI info - done 2024-04-01T07:28:09,955 -- Check for working CXX compiler: /usr/bin/c++ - skipped 2024-04-01T07:28:09,957 -- Detecting CXX compile features 2024-04-01T07:28:09,960 -- Detecting CXX compile features - done 2024-04-01T07:28:09,993 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-04-01T07:28:10,054 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD 2024-04-01T07:28:10,369 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success 2024-04-01T07:28:10,374 -- Found Threads: TRUE 2024-04-01T07:28:10,386 -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF 2024-04-01T07:28:10,486 -- CMAKE_SYSTEM_PROCESSOR: armv7l 2024-04-01T07:28:10,487 -- ARM detected 2024-04-01T07:28:10,491 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E 2024-04-01T07:28:10,804 -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success 2024-04-01T07:28:10,846 CMake Warning (dev) at CMakeLists.txt:28 (install): 2024-04-01T07:28:10,846 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-04-01T07:28:10,847 This warning is for project developers. Use -Wno-dev to suppress it. 2024-04-01T07:28:10,848 CMake Warning (dev) at CMakeLists.txt:37 (install): 2024-04-01T07:28:10,849 Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION. 2024-04-01T07:28:10,849 This warning is for project developers. Use -Wno-dev to suppress it. 2024-04-01T07:28:10,851 -- Configuring done 2024-04-01T07:28:10,916 -- Generating done 2024-04-01T07:28:10,935 -- Build files have been written to: /tmp/tmp9yvzfglc/build 2024-04-01T07:28:10,946 *** Building project with Ninja... 2024-04-01T07:28:14,196 [1/23] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/ggml-alloc.c 2024-04-01T07:28:18,700 [2/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/unicode.cpp 2024-04-01T07:28:18,810 [3/23] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/ggml-backend.c 2024-04-01T07:28:18,987 [4/23] cd /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake 2024-04-01T07:28:18,988 -- Found Git: /usr/bin/git (found version "2.39.2") 2024-04-01T07:28:19,201 [5/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/build-info.cpp 2024-04-01T07:28:30,606 [6/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/unicode-data.cpp 2024-04-01T07:28:41,345 [7/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/sampling.cpp 2024-04-01T07:28:45,983 [8/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/console.cpp 2024-04-01T07:28:57,128 [9/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/grammar-parser.cpp 2024-04-01T07:29:11,734 [10/23] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/ggml-quants.c 2024-04-01T07:29:17,998 [11/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/train.cpp 2024-04-01T07:29:19,882 [12/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/common.cpp 2024-04-01T07:29:19,883 In file included from /usr/include/c++/12/vector:70, 2024-04-01T07:29:19,884 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/grammar-parser.h:14, 2024-04-01T07:29:19,885 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/sampling.h:5, 2024-04-01T07:29:19,886 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/common.h:7, 2024-04-01T07:29:19,887 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/common.cpp:1: 2024-04-01T07:29:19,887 /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const llama_model_kv_override&}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’: 2024-04-01T07:29:19,888 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-04-01T07:29:19,889 439 | vector<_Tp, _Alloc>:: 2024-04-01T07:29:19,890 | ^~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:19,891 /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]’: 2024-04-01T07:29:19,892 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-04-01T07:29:19,893 In file included from /usr/include/c++/12/vector:64: 2024-04-01T07:29:19,894 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-04-01T07:29:19,895 inlined from ‘bool gpt_params_find_arg(int, char**, const std::string&, gpt_params&, int&, bool&)’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/common.cpp:1196:38: 2024-04-01T07:29:19,896 /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 2024-04-01T07:29:19,897 1287 | _M_realloc_insert(end(), __x); 2024-04-01T07:29:19,898 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-04-01T07:29:19,899 In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator]’, 2024-04-01T07:29:19,900 inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/common.cpp:1270:41: 2024-04-01T07:29:19,901 /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 2024-04-01T07:29:19,902 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-04-01T07:29:19,903 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:29,395 [13/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/ngram-cache.cpp 2024-04-01T07:29:31,973 [14/23] /usr/bin/c++ -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/../../common -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/. -O3 -DNDEBUG -MD -MT vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -MF vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o.d -o vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -c /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/quantize.cpp 2024-04-01T07:29:31,974 In file included from /usr/include/c++/12/vector:70, 2024-04-01T07:29:31,975 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/../../common/grammar-parser.h:14, 2024-04-01T07:29:31,976 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/../../common/sampling.h:5, 2024-04-01T07:29:31,977 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/../../common/common.h:7, 2024-04-01T07:29:31,978 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/quantize.cpp:1: 2024-04-01T07:29:31,979 /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]’: 2024-04-01T07:29:31,980 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-04-01T07:29:31,981 439 | vector<_Tp, _Alloc>:: 2024-04-01T07:29:31,982 | ^~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:31,983 /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]’: 2024-04-01T07:29:31,984 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-04-01T07:29:31,985 In member 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]’, 2024-04-01T07:29:31,987 inlined from ‘bool parse_kv_override(const char*, std::vector&)’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/quantize.cpp:242:27, 2024-04-01T07:29:31,988 inlined from ‘int main(int, char**)’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/quantize.cpp:274:56: 2024-04-01T07:29:31,989 /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 2024-04-01T07:29:31,990 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-04-01T07:29:31,991 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:31,992 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]’, 2024-04-01T07:29:31,993 inlined from ‘int main(int, char**)’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/quantize/quantize.cpp:318:34: 2024-04-01T07:29:31,994 /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 2024-04-01T07:29:31,994 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-04-01T07:29:31,995 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:34,357 [15/23] /usr/bin/cc -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/ggml.c 2024-04-01T07:29:36,148 [16/23] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/libggml_static.a && /usr/bin/ar qc vendor/llama.cpp/libggml_static.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o && /usr/bin/ranlib vendor/llama.cpp/libggml_static.a && : 2024-04-01T07:29:37,711 [17/23] /usr/bin/c++ -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/. -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/examples/imatrix/imatrix.cpp 2024-04-01T07:29:38,300 [18/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -O3 -DNDEBUG -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/json-schema-to-grammar.dir/json-schema-to-grammar.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/json-schema-to-grammar.dir/json-schema-to-grammar.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/json-schema-to-grammar.dir/json-schema-to-grammar.cpp.o -c /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/json-schema-to-grammar.cpp 2024-04-01T07:29:38,301 In file included from /usr/include/c++/12/vector:70, 2024-04-01T07:29:38,302 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/json.hpp:32, 2024-04-01T07:29:38,303 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/json-schema-to-grammar.h:2, 2024-04-01T07:29:38,303 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/json-schema-to-grammar.cpp:1: 2024-04-01T07:29:38,304 /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 > >]’: 2024-04-01T07:29:38,304 /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 2024-04-01T07:29:38,305 439 | vector<_Tp, _Alloc>:: 2024-04-01T07:29:38,306 | ^~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:38,306 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 > >]’, 2024-04-01T07:29:38,307 inlined from ‘SchemaConverter::visit(const json&, const std::string&)::’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/json-schema-to-grammar.cpp:617:48: 2024-04-01T07:29:38,308 /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 2024-04-01T07:29:38,308 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-04-01T07:29:38,309 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:29:38,310 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 > >]’, 2024-04-01T07:29:38,310 inlined from ‘std::string SchemaConverter::visit(const json&, const std::string&)’ at /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/common/json-schema-to-grammar.cpp:601:44: 2024-04-01T07:29:38,311 /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 2024-04-01T07:29:38,312 123 | _M_realloc_insert(end(), std::forward<_Args>(__args)...); 2024-04-01T07:29:38,312 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,256 [19/23] /usr/bin/c++ -DGGML_SCHED_MAX_COPIES=4 -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp 2024-04-01T07:30:44,257 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp: In function ‘float* llama_get_logits_ith(llama_context*, int32_t)’: 2024-04-01T07:30:44,258 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:15355:65: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector::size_type’ {aka ‘unsigned int’} [-Wformat=] 2024-04-01T07:30:44,258 15355 | throw std::runtime_error(format("out of range [0, %lu)", ctx->output_ids.size())); 2024-04-01T07:30:44,258 | ~~^ ~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,259 | | | 2024-04-01T07:30:44,259 | long unsigned int std::vector::size_type {aka unsigned int} 2024-04-01T07:30:44,260 | %u 2024-04-01T07:30:44,260 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:15364:89: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 3 has type ‘size_t’ {aka ‘unsigned int’} [-Wformat=] 2024-04-01T07:30:44,261 15364 | throw std::runtime_error(format("corrupt output buffer (j=%d, output_size=%lu)", j, ctx->output_size)); 2024-04-01T07:30:44,261 | ~~^ ~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,262 | | | 2024-04-01T07:30:44,262 | | size_t {aka unsigned int} 2024-04-01T07:30:44,263 | long unsigned int 2024-04-01T07:30:44,263 | %u 2024-04-01T07:30:44,263 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp: In function ‘float* llama_get_embeddings_ith(llama_context*, int32_t)’: 2024-04-01T07:30:44,264 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:15391:65: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector::size_type’ {aka ‘unsigned int’} [-Wformat=] 2024-04-01T07:30:44,264 15391 | throw std::runtime_error(format("out of range [0, %lu)", ctx->output_ids.size())); 2024-04-01T07:30:44,265 | ~~^ ~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,265 | | | 2024-04-01T07:30:44,265 | long unsigned int std::vector::size_type {aka unsigned int} 2024-04-01T07:30:44,266 | %u 2024-04-01T07:30:44,266 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:15400:89: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 3 has type ‘size_t’ {aka ‘unsigned int’} [-Wformat=] 2024-04-01T07:30:44,267 15400 | throw std::runtime_error(format("corrupt output buffer (j=%d, output_size=%lu)", j, ctx->output_size)); 2024-04-01T07:30:44,267 | ~~^ ~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,268 | | | 2024-04-01T07:30:44,268 | | size_t {aka unsigned int} 2024-04-01T07:30:44,269 | long unsigned int 2024-04-01T07:30:44,269 | %u 2024-04-01T07:30:44,269 In file included from /usr/include/c++/12/vector:64, 2024-04-01T07:30:44,270 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.h:1005, 2024-04-01T07:30:44,270 from /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:2: 2024-04-01T07:30:44,271 /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]’: 2024-04-01T07:30:44,271 /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 2024-04-01T07:30:44,272 673 | vector(initializer_list __l, 2024-04-01T07:30:44,272 | ^~~~~~ 2024-04-01T07:30:44,273 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/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*)’: 2024-04-01T07:30:44,273 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4404:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,274 4404 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,274 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,275 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4408:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,275 4408 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,275 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,276 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4410:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,276 4410 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-04-01T07:30:44,277 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,277 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4413:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,277 4413 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,278 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,278 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4447:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,279 4447 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,279 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,280 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4448:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,280 4448 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-04-01T07:30:44,281 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,281 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4449:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,282 4449 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,282 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,283 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4465:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,283 4465 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,284 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,284 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4469:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,284 4469 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,285 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,285 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4470:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,286 4470 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-04-01T07:30:44,286 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,286 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4473:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,287 4473 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,287 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,288 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4513:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,288 4513 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,289 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,289 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4515:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,290 4515 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,290 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,291 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4516:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,291 4516 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,292 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,292 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4529:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,293 4529 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,293 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,294 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4532:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,294 4532 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,295 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,295 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4536:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,295 4536 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,296 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,296 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4541:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,297 4541 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,297 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,298 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4545:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,298 4545 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,298 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,299 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4546:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,299 4546 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,300 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,300 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4548:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,301 4548 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-04-01T07:30:44,301 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,302 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4550:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,302 4550 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-04-01T07:30:44,303 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,304 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4565:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,304 4565 | layer.attn_norm_2 = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd}, false); 2024-04-01T07:30:44,304 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,305 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4568:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,305 4568 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,305 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,306 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4572:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,306 4572 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,307 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,307 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4577:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,308 4577 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,308 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,309 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4578:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,309 4578 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-04-01T07:30:44,310 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,310 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4582:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,311 4582 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,311 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,312 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4583:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,312 4583 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,313 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,313 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4584:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,314 4584 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,315 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,315 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4593:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,315 4593 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,316 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,316 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4596:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,316 4596 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,317 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,317 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4597:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,318 4597 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,318 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,319 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4599:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,319 4599 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,320 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,321 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4600:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,321 4600 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,321 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,322 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4602:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,323 4602 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,323 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,323 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4605:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,324 4605 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-04-01T07:30:44,325 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,325 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4614:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,326 4614 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,326 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,326 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4617:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,327 4617 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,327 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,328 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4618:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,328 4618 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,329 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,329 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4619:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,330 4619 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,330 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,331 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4632:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,331 4632 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,332 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,332 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4635:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,333 4635 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,333 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,334 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4637:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,334 4637 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-04-01T07:30:44,335 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,336 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4640:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,336 4640 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,336 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,337 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4644:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,337 4644 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,338 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,338 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4646:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,339 4646 | layer.attn_q_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {64}); 2024-04-01T07:30:44,339 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,339 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4656:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,340 4656 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,340 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,341 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4657:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,341 4657 | model.type_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_vocab_type}); 2024-04-01T07:30:44,342 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,342 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4659:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,343 4659 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-04-01T07:30:44,343 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,344 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4662:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,344 4662 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,345 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,346 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4663:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,346 4663 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,346 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,347 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4672:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,347 4672 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,348 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,348 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4673:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,348 4673 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-04-01T07:30:44,349 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,349 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4675:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,350 4675 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,350 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,351 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4676:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,352 4676 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,352 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,353 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4678:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,353 4678 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,354 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,354 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4679:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,355 4679 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,355 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,356 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4681:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,357 4681 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,357 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,358 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4684:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,358 4684 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,359 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,359 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4686:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,359 4686 | layer.attn_out_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,360 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,360 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4687:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,361 4687 | layer.attn_out_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,361 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,362 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4689:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,362 4689 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,363 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,363 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4690:65: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,364 4690 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-04-01T07:30:44,364 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,365 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4693:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,365 4693 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,366 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,366 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4694:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,367 4694 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-04-01T07:30:44,368 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,368 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4696:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,368 4696 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-04-01T07:30:44,369 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,369 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4698:64: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,369 4698 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,370 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,370 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4702:66: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,371 4702 | layer.layer_out_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_LAYER_OUT_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,371 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,372 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4707:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,372 4707 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,373 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,373 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4708:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,374 4708 | model.tok_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,374 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,375 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4709:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,375 4709 | model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,376 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,376 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4713:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,377 4713 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,378 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,378 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4714:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,378 4714 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,379 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,379 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4715:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,379 4715 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,380 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,380 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4725:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,381 4725 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,381 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,381 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4734:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,382 4734 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,382 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,383 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4739:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,383 4739 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,384 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,384 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4740:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,385 4740 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-04-01T07:30:44,385 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,386 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4745:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,386 4745 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,387 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,388 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4749:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,388 4749 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,388 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,389 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4750:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,389 4750 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}, false); 2024-04-01T07:30:44,389 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,390 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4752:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,390 4752 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-04-01T07:30:44,391 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,391 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4754:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,392 4754 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU 2024-04-01T07:30:44,392 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,393 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4766:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,393 4766 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,394 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,394 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4769:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,394 4769 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,395 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,395 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4772:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,396 4772 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,396 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,397 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4773:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,398 4773 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, false); 2024-04-01T07:30:44,398 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,398 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4775:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,399 4775 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,399 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,400 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4779:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,400 4779 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, false); 2024-04-01T07:30:44,401 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,401 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4782:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,401 4782 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, false); 2024-04-01T07:30:44,402 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,402 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4785:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,403 4785 | layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false); 2024-04-01T07:30:44,403 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,403 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4790:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,404 4790 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,404 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,405 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4794:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,405 4794 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,406 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,406 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4795:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,406 4795 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,407 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,407 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4796:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,408 4796 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,408 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,409 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4805:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,409 4805 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,409 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,410 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4806:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,410 4806 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,411 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,411 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4808:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,412 4808 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,412 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,412 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4809:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,413 4809 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,413 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,414 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4816:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,414 4816 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}, false); 2024-04-01T07:30:44,415 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,415 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4821:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,416 4821 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,417 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,417 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4822:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,417 4822 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-04-01T07:30:44,418 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,418 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4823:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,418 4823 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,419 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,419 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4828:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,420 4828 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,420 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,420 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4832:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,421 4832 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,421 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,422 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4833:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,423 4833 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,423 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,424 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4842:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,425 4842 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,425 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,426 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4844:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,427 4844 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd*3}); 2024-04-01T07:30:44,427 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,428 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4845:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,428 4845 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd*3}); 2024-04-01T07:30:44,429 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,429 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4848:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,430 4848 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,430 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,431 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4850:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,431 4850 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2}); 2024-04-01T07:30:44,432 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,432 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4852:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,433 4852 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff/2}); 2024-04-01T07:30:44,433 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,434 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4857:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,434 4857 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,435 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,435 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4861:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,436 4861 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,436 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,437 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4862:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,437 4862 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,438 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,438 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4871:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,439 4871 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,440 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,440 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4873:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,440 4873 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,441 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,441 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4874:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,442 4874 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,442 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,443 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4876:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,443 4876 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,444 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,444 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4880:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,445 4880 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,445 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,446 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4881:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,446 4881 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,447 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,447 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4887:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,448 4887 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,448 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,449 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4892:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,449 4892 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,450 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,451 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4896:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,451 4896 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,452 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,452 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4897:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,452 4897 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,453 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,454 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4898:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,454 4898 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,455 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,455 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4899:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,456 4899 | model.output_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "bias"), {n_vocab}); 2024-04-01T07:30:44,456 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,457 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4908:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,457 4908 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,458 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,458 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4909:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,459 4909 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,459 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,460 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4915:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,461 4915 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,461 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,462 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4916:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,463 4916 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-04-01T07:30:44,463 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,463 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4918:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,464 4918 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,465 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,465 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4919:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,466 4919 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,466 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,466 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4921:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,467 4921 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,467 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,468 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4922:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,468 4922 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,469 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,470 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4925:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,470 4925 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,471 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,471 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4926:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,472 4926 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,472 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,473 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4931:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,474 4931 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,474 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,475 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4932:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,475 4932 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-04-01T07:30:44,476 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,476 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4937:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,477 4937 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,478 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,478 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4941:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,479 4941 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,479 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,480 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4942:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,480 4942 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,481 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,481 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4953:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,482 4953 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,482 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,483 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4955:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,484 4955 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,484 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,484 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4959:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,485 4959 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-04-01T07:30:44,486 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,486 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4960:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,487 4960 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,487 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,488 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4965:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,488 4965 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,489 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,489 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4966:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,489 4966 | model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD, "weight"), {n_embd, hparams.n_ctx_train}); 2024-04-01T07:30:44,490 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,490 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4970:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,491 4970 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,491 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,492 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4971:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,493 4971 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,493 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,494 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4972:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,494 4972 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,495 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,495 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4984:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,496 4984 | layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,496 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,497 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4985:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,498 4985 | layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i), {n_embd + 2*n_embd_gqa}); 2024-04-01T07:30:44,498 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,499 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4988:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,499 4988 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,500 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,500 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4990:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,500 4990 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,501 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,501 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4993:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,502 4993 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-04-01T07:30:44,502 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,503 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4994:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,504 4994 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-04-01T07:30:44,504 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,505 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:4997:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,506 4997 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-04-01T07:30:44,506 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,507 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5002:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,508 5002 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,508 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,509 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5006:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,509 5006 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,510 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,511 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5007:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,512 5007 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,512 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,513 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5008:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,514 5008 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,514 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,515 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5017:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,515 5017 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,516 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,517 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5018:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,518 5018 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,518 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,519 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5024:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,520 5024 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,521 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,522 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5026:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,522 5026 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,523 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,524 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5029:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,525 5029 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}); 2024-04-01T07:30:44,525 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,527 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5032:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,527 5032 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,528 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,528 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5033:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,529 5033 | layer.ffn_up_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}); 2024-04-01T07:30:44,530 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,530 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5038:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,531 5038 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,531 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,532 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5040:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,533 5040 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,533 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,534 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5041:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,534 5041 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,535 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,536 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5042:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,536 5042 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,537 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,537 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5054:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,538 5054 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,538 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,539 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5055:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,540 5055 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,540 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,541 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5058:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,541 5058 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,542 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,542 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5059:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,543 5059 | layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,544 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,544 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5068:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,545 5068 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,545 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,546 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5072:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,546 5072 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,547 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,548 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5073:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,548 5073 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,549 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,549 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5084:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,550 5084 | layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,551 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,551 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5085:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,552 5085 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,553 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,553 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5086:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,554 5086 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,554 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,555 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5089:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,555 5089 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,556 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,556 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5092:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,557 5092 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,557 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,558 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5097:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,559 5097 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,559 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,560 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5100:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,561 5100 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,561 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,562 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5101:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,563 5101 | 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 2024-04-01T07:30:44,563 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,564 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5116:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,564 5116 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,565 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,566 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5124:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,566 5124 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,566 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,567 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5131:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,568 5131 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,568 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,569 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5135:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,569 5135 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,570 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,570 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5136:63: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,571 5136 | model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); 2024-04-01T07:30:44,571 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,572 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5138:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,572 5138 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-04-01T07:30:44,573 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,574 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5141:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,574 5141 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,575 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,575 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5154:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,576 5154 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,576 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,577 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5155:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,578 5155 | layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); 2024-04-01T07:30:44,578 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,579 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5158:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,579 5158 | layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,579 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,580 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5159:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,580 5159 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,581 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,581 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5163:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,582 5163 | layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); 2024-04-01T07:30:44,583 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,583 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5164:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,584 5164 | layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,584 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,585 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5165:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,585 5165 | layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i), {n_embd_gqa}); 2024-04-01T07:30:44,586 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,586 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5166:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,592 5166 | layer.bo = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}); 2024-04-01T07:30:44,593 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,597 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5168:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,605 5168 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,606 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,607 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5171:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,607 5171 | layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}); 2024-04-01T07:30:44,608 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,608 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5175:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,609 5175 | layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}); 2024-04-01T07:30:44,609 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,610 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5188:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,610 5188 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,611 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,611 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5192:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,612 5192 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,613 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,614 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5194:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,617 5194 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, false); 2024-04-01T07:30:44,621 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,632 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5197:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,633 5197 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,634 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,634 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5210:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,635 5210 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,635 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,636 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5212:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,637 5212 | layer.ssm_in = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, 2*d_inner}); 2024-04-01T07:30:44,638 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,638 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5214:60: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,638 5214 | layer.ssm_conv1d = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner}); 2024-04-01T07:30:44,639 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,640 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5215:62: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,640 5215 | layer.ssm_conv1d_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner}); 2024-04-01T07:30:44,641 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,641 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5217:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,642 5217 | layer.ssm_x = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_X, "weight", i), {d_inner, dt_rank + 2*d_state}); 2024-04-01T07:30:44,642 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,643 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5219:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,643 5219 | layer.ssm_dt = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_DT, "weight", i), {dt_rank, d_inner}); 2024-04-01T07:30:44,644 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,644 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5220:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,645 5220 | layer.ssm_dt_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_DT, "bias", i), {d_inner}); 2024-04-01T07:30:44,645 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,646 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5223:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,647 5223 | layer.ssm_a = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_A, i), {d_state, d_inner}); 2024-04-01T07:30:44,647 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,648 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5224:55: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,648 5224 | layer.ssm_d = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_SSM_D, i), {d_inner}); 2024-04-01T07:30:44,649 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,649 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5227:57: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,650 5227 | layer.ssm_out = ml.create_tensor(ctx_split, tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}); 2024-04-01T07:30:44,650 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,651 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5232:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,651 5232 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,652 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,652 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5234:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,653 5234 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,653 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,654 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5235:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,654 5235 | model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,655 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,655 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5241:59: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,656 5241 | layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,656 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,657 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5244:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,658 5244 | layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); 2024-04-01T07:30:44,658 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,659 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5245:52: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,659 5245 | layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); 2024-04-01T07:30:44,660 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,661 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5246:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,661 5246 | layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); 2024-04-01T07:30:44,662 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,662 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5247:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,662 5247 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,663 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,663 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5249:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,664 5249 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,664 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,665 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5254:54: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,666 5254 | model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,666 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,667 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5258:61: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,668 5258 | model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); 2024-04-01T07:30:44,669 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,670 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5260:56: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,670 5260 | model.output = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); 2024-04-01T07:30:44,671 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,672 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5278:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,672 5278 | layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,673 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,674 /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/vendor/llama.cpp/llama.cpp:5280:58: note: parameter passing for argument of type ‘std::initializer_list’ changed in GCC 7.1 2024-04-01T07:30:44,675 5280 | layer.ffn_up = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}); 2024-04-01T07:30:44,676 | ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,676 In file included from /usr/include/c++/12/vector:70: 2024-04-01T07:30:44,677 /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]’: 2024-04-01T07:30:44,677 /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector::iterator’ changed in GCC 7.1 2024-04-01T07:30:44,678 439 | vector<_Tp, _Alloc>:: 2024-04-01T07:30:44,679 | ^~~~~~~~~~~~~~~~~~~ 2024-04-01T07:30:44,679 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-04-01T07:30:44,680 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, 2024-04-01T07:30:44,680 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, 2024-04-01T07:30:44,681 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-04-01T07:30:44,682 /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 2024-04-01T07:30:44,682 1287 | _M_realloc_insert(end(), __x); 2024-04-01T07:30:44,683 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-04-01T07:30:44,684 In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator]’, 2024-04-01T07:30:44,685 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, 2024-04-01T07:30:44,686 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, 2024-04-01T07:30:44,686 inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23: 2024-04-01T07:30:44,687 /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 2024-04-01T07:30:44,688 1287 | _M_realloc_insert(end(), __x); 2024-04-01T07:30:44,689 | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ 2024-04-01T07:30:44,800 [20/23] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/libllama.a && /usr/bin/ar qc vendor/llama.cpp/libllama.a vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o vendor/llama.cpp/CMakeFiles/llama.dir/unicode.cpp.o vendor/llama.cpp/CMakeFiles/llama.dir/unicode-data.cpp.o && /usr/bin/ranlib vendor/llama.cpp/libllama.a && : 2024-04-01T07:30:45,142 [21/23] : && /usr/bin/cmake -E rm -f vendor/llama.cpp/common/libcommon.a && /usr/bin/ar qc vendor/llama.cpp/common/libcommon.a vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/sampling.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/console.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/grammar-parser.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/train.cpp.o vendor/llama.cpp/common/CMakeFiles/common.dir/ngram-cache.cpp.o && /usr/bin/ranlib vendor/llama.cpp/common/libcommon.a && : 2024-04-01T07:30:45,212 [22/23] : && /usr/bin/c++ -O3 -DNDEBUG vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o vendor/llama.cpp/examples/quantize/CMakeFiles/quantize.dir/quantize.cpp.o -o vendor/llama.cpp/examples/quantize/quantize vendor/llama.cpp/libllama.a && : 2024-04-01T07:30:45,553 [23/23] : && /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 && : 2024-04-01T07:30:45,557 *** Installing project into wheel... 2024-04-01T07:30:45,593 -- Install configuration: "Release" 2024-04-01T07:30:45,597 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/lib/cmake/Llama/LlamaConfig.cmake 2024-04-01T07:30:45,600 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/lib/cmake/Llama/LlamaConfigVersion.cmake 2024-04-01T07:30:45,604 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/include/ggml.h 2024-04-01T07:30:45,609 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/include/ggml-alloc.h 2024-04-01T07:30:45,611 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/include/ggml-backend.h 2024-04-01T07:30:45,614 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/lib/libllama.a 2024-04-01T07:30:45,644 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/include/llama.h 2024-04-01T07:30:45,649 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/bin/convert.py 2024-04-01T07:30:45,654 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/bin/convert-lora-to-ggml.py 2024-04-01T07:30:45,659 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/bin/quantize 2024-04-01T07:30:45,748 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/bin/imatrix 2024-04-01T07:30:45,842 -- Installing: /tmp/tmp9yvzfglc/wheel/platlib/llama_cpp/libllama.a 2024-04-01T07:30:45,871 -- Installing: /tmp/pip-wheel-81m8m71x/llama-cpp-conv_0b2ff87694d240fc8c0365014a39fb77/llama_cpp/libllama.a 2024-04-01T07:30:45,907 *** Making wheel... 2024-04-01T07:30:47,598 *** Created llama_cpp_conv-0.2.58-cp311-cp311-manylinux_2_36_armv7l.whl... 2024-04-01T07:30:47,656 Building wheel for llama-cpp-conv (pyproject.toml): finished with status 'done' 2024-04-01T07:30:47,689 Created wheel for llama-cpp-conv: filename=llama_cpp_conv-0.2.58-cp311-cp311-manylinux_2_36_armv7l.whl size=2841576 sha256=a504bddb2611e155118405ded0c673b0a619cc98f84d89e3ac487eb2a6ab2fa7 2024-04-01T07:30:47,690 Stored in directory: /tmp/pip-ephem-wheel-cache-bj0ha7nk/wheels/76/d1/d5/9528217e0093b9bd25981ee89fd12c6ba6aae445f0cf6b01ef 2024-04-01T07:30:47,703 Successfully built llama-cpp-conv 2024-04-01T07:30:47,780 Removed build tracker: '/tmp/pip-build-tracker-rqnice_z'