pygmo is a scientific Python library for massively parallel optimization. It is built around the idea of providing a unified interface to optimization algorithms and to optimization problems and to make their deployment in massively parallel environments easy.

If you are using pygmo as part of your research, teaching, or other activities, we would be grateful if you could star the repository and/or cite our work. For citation purposes, you can use the following BibTex entry, which refers to the pygmo paper in the Journal of Open Source Software:

@article{Biscani2020,
  doi = {10.21105/joss.02338},
  url = {https://doi.org/10.21105/joss.02338},
  year = {2020},
  publisher = {The Open Journal},
  volume = {5},
  number = {53},
  pages = {2338},
  author = {Francesco Biscani and Dario Izzo},
  title = {A parallel global multiobjective framework for optimization: pagmo},
  journal = {Journal of Open Source Software}
}

The DOI of the latest version of the software is available at this link.

The full documentation can be found here.

pygmo relies on Python's pickle module (and, by default, on cloudpickle) to (de)serialise user-defined problems, algorithms, islands, etc., including within population, archipelago, problem, algorithm, bfe, island, r_policy, s_policy and topology objects. As with the standard pickle module, deserialising (unpickling) data is equivalent to arbitrary code execution. Never unpickle, load archipelago/island checkpoints, or otherwise deserialise pygmo objects coming from an untrusted or unauthenticated source.

The recommended installation route is via conda-forge:

conda install -c conda-forge pygmo

You can also install from PyPI:

pip install pygmo

At the moment, PyPI wheels are provided for Linux x86_64 and Linux aarch64 only. For other platforms, please use conda-forge or build from source.