2025MNRAS.540.3121C

Galaxy-galaxy strong lensing provides a powerful probe of galaxy formation, evolution, and the properties of dark matter and dark energy. However, conventional lens-modelling approaches are computationally expensive and require fine-tuning to avoid local optima, rendering them impractical for the hundreds of thousands of lenses expected from surveys such as Euclid, China Space Station Telescope, and Roman Space Telescopes. To overcome these challenges, we introduce TinyLensGPU, a GPU-accelerated lens-modelling tool that employs Accelerated Linear Algebra-based acceleration with JAX and a neural-network-enhanced nested sampling algorithm, nautilus-sampler. Tests on 1000 simulated galaxy-galaxy lenses demonstrate that on an RTX 4060 Ti GPU, TinyLensGPU achieves likelihood evaluations approximately 2000 times faster than traditional methods. Moreover, the nautilus-sampler reduces the number of likelihood evaluations by a factor of 3, decreasing the overall modelling time per lens from several days to roughly 3 min. Application to 63 SLACS lenses observed by the Hubble Space Telescope recovers Einstein radii consistent with the literature values (within $\lesssim 5~{{\ \rm per\ cent}}$ deviation), which is within known systematic uncertainties. Catastrophic failures, where the sampler becomes trapped in local optima, occur in approximately 5 per cent of the simulated cases and 10 per cent of the SLACS sample. We argue that such issues are inherent to automated lens modelling but can be mitigated by incorporating prior knowledge from machine learning techniques. This work thus marks a promising step towards the efficient analysis of strong lenses in the era of big data. The code and data are available at https://github.com/caoxiaoyue/TinyLensGpu.