How optical computing can accelerate the UK’s generative AI sector

There are three major bottlenecks facing current computing hardware: computing speed, power consumption and memory bandwidth.

These hardware bottlenecks are limiting the progress of AI and especially generative models, or large language models. We are in dire need of a new computing paradigm to support the next generation of AI. This is a topic our co-founder, Xianxin Guo, explored in this latest article for UKTN.

So, where does Lumai fit into this challenge? Leveraging light to perform the bulk of AI computation, we are committed to enabling AI acceleration with fully optical computing that offers speeds up to 1000 times faster, while consuming far less energy than traditional electronics.

Lumai’s optical computing technology can combat the current bottlenecks facing traditional electronics to deliver game-changing impact in the world of AI.

Want to find out more? Read the full article here.

To keep up with the latest Lumai updates, follow us on LinkedIn.