A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Proposes adding an arm64 macOS CI job testing the R package. CRAN checks every submission on an arm64 Mac (https://cran.r-project.org/web/checks/check_flavors.html), so hopefully this will help catch issues before attempting submissions to CRAN.
To avoid further growing the CI matrix, this proposes dropping the job that tests the R package compiled with clang on Linux with R 3.6. I think that's ok, because there are others covering compiling the R package with gcc on Linux
Fixes #6481
Proposes adding an arm64 macOS CI job testing the R package. CRAN checks every submission on an arm64 Mac (https://cran.r-project.org/web/checks/check_flavors.html), so hopefully this will help catch issues before attempting submissions to CRAN.
To avoid further growing the CI matrix, this proposes dropping the job that tests the R package compiled with
clang
on Linux with R 3.6. I think that's ok, because there are others covering compiling the R package withgcc
on Linuxhttps://github.com/microsoft/LightGBM/blob/fc788a51b61368f78246e5c450f0ea77d263eb2b/.github/workflows/r_package.yml#L58-L63
And because we're planning to move away from supporting R 3.6: https://github.com/microsoft/LightGBM/pull/6442#issuecomment-2159162313
This should also reduce the manual testing effort for releases: https://github.com/microsoft/LightGBM/pull/6439#issuecomment-2167206451