Lightweight Gaussian Process Inference in C++ on Metal and CUDA

arXiv:2605.17898v1 Announce Type: new Abstract: Gaussian process (GP) inference in Python is dominated by libraries such as GPyTorch and GPflow, which are built on deep-learning frameworks and inherit their dispatch overhead and dependency footprint. We present LightGP, a dependency-free C++17 library for GP regression with Python bindings, supporting Apple Metal and NVIDIA CUDA backends alongside tuned CPU paths via Apple Accelerate and OpenBLAS. LightGP provides four inference paths -- exact Cholesky, matrix-free conjugate gradients, sparse variational free energy, and structured kernel interpolation with FFT -- covering problems from N{=}100 to N{=}500{,}000. On an Apple M4, LightGP CPU is 2.6--8.7imes faster than GPyTorch CPU for exact GP and {sim}1.5imes faster for sparse GP at every scale tested. On an NVIDIA RTX~3060, LightGP CUDA is 2.3--6.7imes faster than GPyTorch CUDA for exact GP up to N{=}2{,}048, with GPyTorch closing the gap at N{=}4{,}096. A fused matrix-free kernel-vector product on Metal achieves 32imes over the explicit path at N{=}20{,}000 with O(N) memory, and an FFT-accelerated SKI matvec via Accelerate vDSP runs in sub-millisecond time at N{=}200{,}000. LightGP compiles as a single static library with zero external dependencies and is installable via exttt{pip install lightgp

Source: arXiv cs.LG | 2026-05-19