KBaba7/llama.cpp

1# CI2 3In addition to [Github Actions](https://github.com/ggerganov/llama.cpp/actions) `llama.cpp` uses a custom CI framework:4 5https://github.com/ggml-org/ci6 7It monitors the `master` branch for new commits and runs the8[ci/run.sh](https://github.com/ggerganov/llama.cpp/blob/master/ci/run.sh) script on dedicated cloud instances. This allows us9to execute heavier workloads compared to just using Github Actions. Also with time, the cloud instances will be scaled10to cover various hardware architectures, including GPU and Apple Silicon instances.11 12Collaborators can optionally trigger the CI run by adding the `ggml-ci` keyword to their commit message.13Only the branches of this repo are monitored for this keyword.14 15It is a good practice, before publishing changes to execute the full CI locally on your machine:16 17```bash18mkdir tmp19 20# CPU-only build21bash ./ci/run.sh ./tmp/results ./tmp/mnt22 23# with CUDA support24GG_BUILD_CUDA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt25 26# with SYCL support27source /opt/intel/oneapi/setvars.sh28GG_BUILD_SYCL=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt29```30