OPPO implements MoE architecture on mobile devices, improving AI processing efficiency by 40%.

OPPO has become the first company to implement the Mixture of Experts (MoE) architecture on mobile devices, enhancing AI processing efficiency. This innovation enables faster AI task execution, with lab tests indicating a 40% speed improvement and better energy efficiency. The MoE architecture allows for specialized sub-models to handle specific tasks, contributing to faster responses, longer battery life, and improved privacy. OPPO aims to make advanced AI capabilities more accessible across its device range.

October 23, 2024
12 Articles