numpyro

Probabilistic programming library built on top of NumPy and JAX, designed for flexible and efficient Bayesian modeling. It leverages JAX's automatic differentiation and GPU/TPU acceleration capabilities to provide a high-performance environment for statistical modeling and inference, supporting various inference algorithms like Hamiltonian Monte Carlo (HMC) and No-U-Turn Sampler (NUTS). NumPyro is particularly useful for researchers and data scientists who require scalable and flexible tools for complex statistical modeling.

numpyro was discovered on October 30th 2022 and it currently has a search volume of 1.6K with a growth of +614%.