MacMusic  |  PcMusic  |  440 Software  |  440 Forums  |  440TV  |  Zicos
its
Search

xAI picked Ethernet over InfiniBand for its H100 Colossus training cluster

Tuesday October 29, 2024. 08:30 PM , from TheRegister
Work already underway to expand system to 200,000 Nvidia Hopper chips
Unlike most AI training clusters, xAI's Colossus with its 100,000 Nvidia Hopper GPUs doesn't use InfiniBand. Instead, the massive system, which Nvidia bills as the 'world's largest AI supercomputer,' was built using the GPU giant's Spectrum-X Ethernet fabric.…
Read more at TheRegister
https://go.theregister.com/feed/www.theregister.com/2024/10/29/xai_colossus_networking/

Related News

its Microsoft turning away AI training workloads – inferencing makes better money TheRegisterOct 31
colossus Meta’s Next Llama AI Models Are Training on a GPU Cluster ‘Bigger Than Anything’ Else Wired: Tech.Oct 31
nvidia 6 Prompt Engineering Courses: Free Training for Beginners eWeekOct 28
infiniband Contractors training Amazon, Meta and Microsoft’s AI systems left without pay after Appen moves to new platform OS NewsOct 25
training Intern allegedly messed with ByteDance's LLM training cluster TheRegisterOct 22
ethernet Planned Adobe app to put an end to AI training on images and clips ComputerWorldOct 9
over Security awareness training is not enough to stop breaches BetaNewsOct 9
picked Meta Confirms It Will Use Ray-Ban Smart Glasses Images for AI Training SlashdotOct 3
hopper Zyxel launches Wi-Fi 7 gateways with advanced 10G Ethernet capabilities BetaNewsOct 3
xai Meta Hit With New Author Copyright Lawsuit Over AI Training SlashdotOct 3
cluster This Startup Wants YouTube Creators to Get Paid for AI Training Data Wired: Tech.Sep 30
system OpenAI to reveal secret training data in copyright case – for lawyers' eyes only TheRegisterSep 26
News copyright owned by their original publishers | Copyright © 2004 - 2024 Zicos / 440Network
Current Date
Oct, Thu 31 - 13:14 CET