Felipe97/llama-cpp-compiled

1# CI2 3This CI implements heavy-duty workflows that run on self-hosted runners. Typically the purpose of these workflows is to4cover hardware configurations that are not available from Github-hosted runners and/or require more computational5resource than normally available.6 7It is a good practice, before publishing changes to execute the full CI locally on your machine. For example:8 9```bash10mkdir tmp11 12# CPU-only build13bash ./ci/run.sh ./tmp/results ./tmp/mnt14 15# with CUDA support16GG_BUILD_CUDA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt17 18# with SYCL support19source /opt/intel/oneapi/setvars.sh20GG_BUILD_SYCL=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt21 22# with MUSA support23GG_BUILD_MUSA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt24 25# etc.26```27 28# Adding self-hosted runners29 30- Add a self-hosted `ggml-ci` workflow to [[.github/workflows/build.yml]] with an appropriate label31- Request a runner token from `ggml-org` (for example, via a comment in the PR or email)32- Set-up a machine using the received token ([docs](https://docs.github.com/en/actions/how-tos/manage-runners/self-hosted-runners/add-runners))33- Optionally update [ci/run.sh](https://github.com/ggml-org/llama.cpp/blob/master/ci/run.sh) to build and run on the target platform by gating the implementation with a `GG_BUILD_...` env34