Welcome to torchquad’s documentation!

torchquad is a Python3 module for multidimensional numerical integration on the GPU. It uses autoray to support PyTorch and other machine learning modules.

You can see the latest code at https://github.com/esa/torchquad.

Overview:

• Getting started
  • Prerequisites
  • Installation
  • Usage
• Tutorial
  • Minimal working example
  • Detailed Introduction
  • Outline
  • Imports
  • One-dimensional integration
  • High-dimensional integration
  • Comparison with scipy
  • Using different backends with torchquad
  • Computing gradients with respect to the integration domain
  • Speedups for repeated quadrature
• Integration methods
  • Stochastic Methods
  • Deterministic Methods
• All content
  • Boole
  • IntegrationGrid
  • MonteCarlo
  • RNG
  • Simpson
  • Trapezoid
  • VEGAS
  • enable_cuda()
  • plot_convergence()
  • plot_runtime()
  • set_log_level()
  • set_precision()
  • set_up_backend()
  • NewtonCotes
  • BaseIntegrator

Contact:

• Contact information
• Contributing

Roadmap

See the open issues for a list of proposed features (and known issues).

License

Distributed under the GPL-3.0 License. See LICENSE for more information.

Indices and tables

• Index

• Module Index

• Search Page