{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/11"}],"enrichment":{"capability":"Zuko implements normalizing flows in PyTorch as trainable neural modules, enabling conditional probability distributions and transformations that can be sent to GPU and optimized with standard PyTorch workflows.","skillfed_tags":["probabilistic-modeling","generative-models","variational-inference"],"use_cases":["Train a neural spline flow to model complex conditional distributions for density estimation or variational inference tasks.","Build custom generative models by composing flow components like masked autoregressive transforms and base distributions.","Implement probabilistic inference pipelines where conditional distributions must be parameterized by neural networks.","Experiment with different normalizing flow architectures (RealNVP, MAF, NSF, etc.) for research or production density modeling.","Sample from learned conditional distributions p(x|c) after training a flow on paired data."],"what_it_does":"Zuko bridges a gap in PyTorch's probabilistic modeling: the built-in Distribution and Transform classes cannot be sent to GPU or treated as trainable modules. Zuko wraps these concepts in LazyDistribution and LazyTransform\u2014modules whose forward pass returns a distribution or transformation\u2014enabling conditional probability modeling and normalizing flows to work seamlessly within PyTorch's training pipeline.\n\nThe package provides a suite of flow architectures (NSF, RealNVP, MAF, NICE, and others) that can be instantiated with configurable hyperparameters and trained end-to-end. It also supports custom flows built from individual components like masked autoregressive transforms and rotation transforms, making it suitable for both standard use cases and research-driven extensions.","worth_installing":"Yes. Zuko fills a genuine need in PyTorch's probabilistic modeling ecosystem\u2014making normalizing flows trainable and GPU-compatible. It is actively maintained, has no known vulnerabilities, low install friction, and a permissive MIT license. Install it if you need conditional probability distributions or flow-based generative models in PyTorch."},"id":"zuko","links":{"html":"https://skillfed.io/packages/zuko","md":"https://skillfed.io/packages/zuko.md","pypi":"https://pypi.org/project/zuko/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-03-10","license_spdx":"MIT","license_treatment":"permissive","name":"zuko","python_support":"supports_current","summary":"Normalizing flows in PyTorch"},"popularity":{"monthly_downloads":76257,"position":14640,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"1.6.0"}