PyTorch 2.10 is out today as the latest feature update to this widely-used deep learning library. ## Key improvements The new PyTorch release continues improving support for Intel GPUs as well as for the AMD ROCm compute stack along with still driving more enhancements for NVIDIA CUDA. The aim is to provide developers with increasingly powerful and versatile tools for training and inference of deep learning models on various hardware platforms. PyTorch is one of the leading frameworks in the world of machine learning, used in both academic and industrial settings. Its flexibility and wide range of features make it suitable for a wide variety of applications, from computer vision to natural language processing.