Skip to content


Normalizing-flow enhanced sampling package for probabilistic inference

flowMC is a Jax-based python package for normalizing-flow enhanced Markov chain Monte Carlo (MCMC) sampling. The code is open source under MIT license, and it is under active development.

  • Just-in-time compilation is supported.
  • Native support for GPU acceleration.
  • Suit for problems with multi-modality and complex geometry.

Five steps to use flowMC's guide¤

  1. You will find basic information such as installation and a quick guide in the quickstart.
  2. We give more information about tuning parameters of our sampler in the configuration_guide.
  3. In tutorials, we have a set of more pedagogical notebooks that will give you a better understanding of the package infrastructure.
  4. We list some community examples in community_example, so users can see whether there is a similar use case they can adopt their code quickly.
  5. Finally, we have a list of frequently asked questions in FAQ.