pyro-ppl/pyro
Deep universal probabilistic programming with Python and PyTorch
Supports automatic inference through variational inference and Markov chain Monte Carlo samplers, with composable effect handlers enabling custom inference algorithms without modifying model code. Built on PyTorch's autograd for efficient gradient-based inference at scale. Integrates with NumPyro for JAX-based inference and provides specialized modules for time-series modeling, causal inference, and experimental design optimization.
8,989 stars and 1,262,278 monthly downloads. Used by 10 other packages. No commits in the last 6 months. Available on PyPI.
Stars
8,989
Forks
1,005
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 09, 2025
Monthly downloads
1,262,278
Commits (30d)
0
Dependencies
5
Reverse dependents
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pyro-ppl/pyro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
erdogant/bnlearn
Python package for Causal Discovery by learning the graphical structure of Bayesian networks....
astro-informatics/harmonic
Machine learning assisted marginal likelihood (Bayesian evidence) estimation for Bayesian model selection
cdslaborg/paramonte
ParaMonte: Parallel Monte Carlo and Machine Learning Library for Python, MATLAB, Fortran, C++, C.
tensorflow/probability
Probabilistic reasoning and statistical analysis in TensorFlow
google/edward2
A simple probabilistic programming language.