This new whitepaper from AMD explores uses cases as well as AMD EPYC processor advancements and performance that benefit AI inference
While AI training is extremely data- and processing-intensive, AI inference, where the trained model processes incoming data in real time, can be done economically with off-the-shelf servers equipped with AMD EPYC™ processors. With up to 96 cores per 4th Gen AMD EPYC processor, these servers can accelerate a range of data center and edge applications including customer support, retail, automotive, financial services, medical, and manufacturing.
NextComputing deployable servers featuring AMD EPYC processors are a highly economical solution for AI inferencing near your data, whether at the core or the edge.