AMD joins UXL Foundation as steering member, backs oneDNN for PyTorch
Photo: Crypto Briefing
AMD and Intel agree to make oneDNN the default open-source library for x86 CPU acceleration in PyTorch AMD has joined the UXL Foundation as a steering member. The move is designed to push forward work on integrating the oneDNN library with PyTorch, one of the most widely used frameworks for building deep learning models. AMD and Intel, who have competed for decades over the CPU market, have agreed to make oneDNN the default open-source library for x86 acceleration in PyTorch. AMD’s new role became official on October 20, 2026.
Source: Crypto Briefing
