mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-04 02:37:27 +02:00
Daniel Bevenius
bd4372fdac
This commit removes the nightly/release information that I added previously to keep this focused only on using building and installing llama.cpp with cmake and being able to quickly verify changes or troubleshoot issues.
1.4 KiB
1.4 KiB
cmake-test
This is just for manually testing/developing of a llama.cpp installation to enable troubleshooting issues and exploration. The idea is that this can be used after making changes to llama.cpp installation cmake configuration and then verify it locally.
Usage
The following will configure, build, and install llama.cpp
Configuring/build/install:
./build-install.sh
The above command will create a directory named install in the current directory
which will have the follwing files in its lib directory:
(venv) $ ls install/lib/
cmake libggml.so libllama-common.so.0 libllama.so.0.1.0 llama.cpp
libggml-base.so libggml.so.0 libllama-common.so.0.1.0 libmtmd.so pkgconfig
libggml-base.so.0 libggml.so.0.19.0 libllama.so libmtmd.so.0
libggml-base.so.0.19.0 libllama-common.so libllama.so.0 libmtmd.so.0.1.0
Build/run this project using the installation created above:
(venv) $ ./build.sh
-- Configuring done (0.0s)
-- Generating done (0.0s)
-- Build files have been written to: /home/danbev/work/ai/llama.cpp/examples/test-cmake/build
[100%] Built target test-cmake
[test-cmake] Using llama.cpp version 0.1.0-dev-b10335
[test-cmake] Initializing backend...
load_backend: loaded CPU backend from /home/danbev/work/ai/llama.cpp/examples/test-cmake/install/lib/llama.cpp/libggml-cpu-alderlake.so
[test-cmake] Backend initialized.