GPU上的内核操作，使用自动区分，无内存溢出
Kernel Operations on the GPU, with Autodiff, without Memory Overflows
摘要：
KeOps库为张量提供了快速且内存高效的GPU支持，张量的条目由数学公式给出，例如内核和距离矩阵。KeOps解决了以张量为中心的库在内核和几何应用中的主要瓶颈：内存消耗。它还支持自动微分，性能优于标准GPU基线，包括PyTorch CUDA张量或Halide和TVM库。KeOps将优化的C++/CUDA方案与用于高级语言的绑定器相结合：Python（Numpy和PyTorch）、Matlab和GNU R。因此，高级“二次”代码现在可以扩展到大型数据集，在几秒钟内处理数百万个样本。KeOps为内核方法带来了类似图形的性能，并且可以在标准存储库（PyPi，CRAN）上免费获得。为了展示其多功能性，我们在\url{www.kernel-operations.io}上提供了各种设置的在线教程。
英文摘要：
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. It also supports automatic differentiation and outperforms standard GPU baselines, including PyTorch CUDA tensors or the Halide and TVM libraries. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and GNU R. As a result, high-level "quadratic" codes can now scale up to large data sets with millions of samples processed in seconds. KeOps brings graphics-like performances for kernel methods and is freely available on standard repositories (PyPi, CRAN). To showcase its versatility, we provide tutorials in a wide range of settings online at \url{www.kernel-operations.io}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
