`cibuildwheel` is here to help. `cibuildwheel` runs on your CI server - currently it supports Azure Pipelines, Travis CI, AppVeyor, and CircleCI - and it builds and tests your wheels across all of your platforms.
- Bundles shared library dependencies on Linux and macOS through [auditwheel](https://github.com/pypa/auditwheel) and [delocate](https://github.com/matthew-brett/delocate)
- Runs the library test suite against the wheel-installed version of your library
`cibuildwheel` currently works **Travis CI** and **CircleCI** to build Linux and Mac wheels, and **AppVeyor** to build Windows wheels. **Azure Pipelines** supports all three.
`cibuildwheel` is not intended to run on your development machine. It will try to install packages globally; this is no good. Travis CI, CircleCI, and AppVeyor run their builds in isolated environments, so are ideal for this kind of script.
Since `cibuildwheel` runs the wheel through delocate or auditwheel, it might automatically bundle dynamically linked libraries from the build machine.
It helps ensure that the library can run without any dependencies outside of the pip toolchain.
This is similar to static linking, so it might have some licence implications. Check the license for any code you're pulling in to make sure that's allowed.
- ⭐️ @matthew-brett for [matthew-brett/multibuild](http://github.com/matthew-brett/multibuild) and [matthew-brett/delocate](http://github.com/matthew-brett/delocate)
-@PyPA for the manylinux Docker images [pypa/manylinux](https://github.com/pypa/manylinux)
-@ogrisel for [wheelhouse-uploader](https://github.com/ogrisel/wheelhouse-uploader) and `run_with_env.cmd`
If you'd like to keep wheel building separate from the package itself, check out [astrofrog/autowheel](https://github.com/astrofrog/autowheel). It builds packages using cibuildwheel from source distributions on PyPI.
If `cibuildwheel` is too limited for your needs, consider [matthew-brett/multibuild](http://github.com/matthew-brett/multibuild). `multibuild` is a toolbox for building a wheel on various platforms. It can do a lot more than this project - it's used to build SciPy!