Felipe97/llama-cpp-compiled

1## cmake-test2 3This is just for manually testing/developing of a llama.cpp installation to4enable troubleshooting issues and exploration. The idea is that this can be used5after making changes to llama.cpp installation cmake configuration and then6verify it locally.7 8### find_package9The following will configure, build, and install llama.cpp, and the build a10project that uses find_package to use the installation.11 12Configuring/build/install:13```console14./build-install.sh15```16The above command will create a directory named `install` in the current directory17which will have the following files in its lib directory:18```console19$ ls install/lib/20cmake                   libggml.so          libllama-common.so.0      libllama.so.0.1.0  llama.cpp21libggml-base.so         libggml.so.0        libllama-common.so.0.1.0  libmtmd.so         pkgconfig22libggml-base.so.0       libggml.so.0.19.0   libllama.so               libmtmd.so.023libggml-base.so.0.19.0  libllama-common.so  libllama.so.0             libmtmd.so.0.1.024```25 26Build/run this project using the installation created above:27```console28$ ./build.sh29-- Configuring done (0.0s)30-- Generating done (0.0s)31-- Build files have been written to: /path/to/llama.cpp/examples/test-cmake/build32[100%] Built target test-cmake33[test-cmake] Using llama.cpp version 0.1.0-dev-b1033534[test-cmake] Initializing backend...35load_backend: loaded CPU backend from /path/to/llama.cpp/examples/test-cmake/install/lib/llama.cpp/libggml-cpu-alderlake.so36[test-cmake] Backend initialized.37```38 39### add_subdirectory40The following will use add_subdirectory to include llama.cpp in a cmake project41and is intended to simulate projects that build llama.cpp in this way.42 43```console44$ USE_SUBDIR=ON ./build.sh45```46