Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

ARIA to Test Lumai Iris Optical AI Servers in a Data Centre

AI summary

ARIA’s Scaling Inference Lab plans to install Lumai’s Iris servers as its first optical computing platform and test them across several machines in a commercial data centre. The trials will assess real AI models, power consumption and cooling, according to The Next Web. Lumai says the light-based system could reduce data-centre power use by up to 90% and be at least 16 times more energy-efficient per request when paired with standard chips, but those figures have not been independently checked.

In-depth insight

The planned deployment will test whether optical computing can handle real AI inference workloads under data-centre power and cooling conditions.

UK’s ARIA will test Lumai’s light-based AI servers in a data centre
Credit: Omar:. Lopez-Rincon on Unsplash
Image Credits
Credit: Omar:. Lopez-Rincon on Unsplash

ARIA’s Scaling Inference Lab will deploy Lumai’s Iris servers, which use beams of light to run AI calculations, as its first optical platform. Lumai claims big energy savings, but these have not been independently tested. The lab will test the servers in a commercial data centre.

The UK’s Advanced Research and Invention Agency (ARIA) will test servers that use light to run AI models, in a lab it funds, Oxford startup Lumai said on Tuesday.

The Scaling Inference Lab, backed by £50M from ARIA and run by the nonprofit CommonAI, will install Lumai’s Iris servers as its first optical computing platform. It will run them across several machines in a commercial data centre, to see how they cope with real AI models, power and cooling.

#Lumai#ARIA Scaling Inference Lab#Lumai Iris servers#CommonAI#Oxford University

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.