Kernel Operations on the GPU, with Autodiff, without Memory Overflows

The 'KeOps' library lets you compute generic reductions of very large arrays whose entries are given by a mathematical formula. It combines a tiled reduction scheme with an automatic differentiation engine, and can be used through 'R', 'Matlab', 'NumPy' or 'PyTorch' backends. It is perfectly suited to the computation of Kernel dot products and the associated gradients, even when the full kernel matrix does not fit into the GPU memory.


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("rkeops") by Ghislain Durif, 2 months ago,

Report a bug at

Browse source code at

Authors: Benjamin Charlier [aut] (<>) , Jean Feydy [aut] (<>) , Joan A. Glaunès [aut] (<>) , Ghislain Durif [aut, cre] (<>) , François-David Collin [ctb] (Development-related consulting and support) , Daniel Frey [ctb] (Author of the included C++ library 'sequences')

Documentation:   PDF Manual  

MIT + file LICENSE license

Imports Rcpp, openssl, stringr

Suggests testthat, knitr, rmarkdown

Linking to Rcpp, RcppEigen

System requirements: C++11, cmake (>= 3.10), clang (optional), CUDA (optional but recommended)

See at CRAN