GPyTorch is a Gaussian process library implemented using PyTorch. GPyTorch is designed for creating scalable, flexible, and modular Gaussian process models with ease.

Internally, GPyTorch differs from many existing approaches to GP inference by performing most inference operations using numerical linear algebra techniques like preconditioned conjugate gradients. Implementing a scalable GP method is as simple as providing a matrix multiplication routine with the kernel matrix and its derivative via our LinearOperator interface, or by composing many of our already existing LinearOperators. This allows not only for easy implementation of popular scalable GP techniques, but often also for significantly improved utilization of GPU computing compared to solvers based on the Cholesky decomposition.

GPyTorch provides (1) significant GPU acceleration (through MVM based inference); (2) state-of-the-art implementations of the latest algorithmic advances for scalability and flexibility (SKI/KISS-GP, stochastic Lanczos expansions, LOVE, SKIP, stochastic variational deep kernel learning, ...); (3) easy integration with deep learning frameworks.

See our documentation, examples, tutorials on how to construct all sorts of models in GPyTorch.

Requirements:

• Python >= 3.8
• PyTorch >= 1.11

Install GPyTorch using pip or conda:

pip install gpytorch
conda install gpytorch -c gpytorch

(To use packages globally but install GPyTorch as a user-only package, use pip install --user above.)

To upgrade to the latest (unstable) version, run

pip install --upgrade git+https://github.com/cornellius-gp/linear_operator.git
pip install --upgrade git+https://github.com/cornellius-gp/gpytorch.git

If you are contributing a pull request, it is best to perform a manual installation:

git clone https://github.com/cornellius-gp/gpytorch.git
cd gpytorch
pip install -e .[dev,docs,examples,keops,pyro,test]  # keops and pyro are optional

Note: Experimental AUR package. For most users, we recommend installation by conda or pip.

GPyTorch is also available on the ArchLinux User Repository (AUR). You can install it with an AUR helper, like yay, as follows:

yay -S python-gpytorch

To discuss any issues related to this AUR package refer to the comments section of python-gpytorch.

If you use GPyTorch, please cite the following papers:

Gardner, Jacob R., Geoff Pleiss, David Bindel, Kilian Q. Weinberger, and Andrew Gordon Wilson. "GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration." In Advances in Neural Information Processing Systems (2018).

@inproceedings{gardner2018gpytorch,
  title={GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration},
  author={Gardner, Jacob R and Pleiss, Geoff and Bindel, David and Weinberger, Kilian Q and Wilson, Andrew Gordon},
  booktitle={Advances in Neural Information Processing Systems},
  year={2018}
}

See the contributing guidelines CONTRIBUTING.md for information on submitting issues and pull requests.

GPyTorch is primarily maintained by:

• Jake Gardner (University of Pennsylvania)
• Geoff Pleiss (Columbia University)
• Kilian Weinberger (Cornell University)
• Andrew Gordon Wilson (New York University)
• Max Balandat (Meta)

We would like to thank our other contributors including (but not limited to) Eytan Bakshy, Wesley Maddox, Ke Alexander Wang, Ruihan Wu, Sait Cakmak, David Eriksson, Sam Daulton, Martin Jankowiak, Sam Stanton, Zitong Zhou, David Arbour, Karthik Rajkumar, Bram Wallace, Jared Frank, and many more!

Development of GPyTorch is supported by funding from the Bill and Melinda Gates Foundation, the National Science Foundation, SAP, the Simons Foundation, and the Gatsby Charitable Trust.

GPyTorch is MIT licensed.