DGX B200, DGX GB200, and the DGX GB200 SuperPOD

720 petaflops of training performance, 1.4 exaflops of inference

Here's what's coming to a data center near you

Using AI to make chips better at AI

Inference chip developer hopes to ship 1.5m LPUs

Newly-launched state-backed AI fund MGX in talks with Sam Altman

And is building its third supercomputer, alongside plans for Qualcomm inference chip deployments

A role not for the faint of heart

As GPU TDPs look set to pass 1kW

Already working with Microsoft on Maia AI Accelerator development

In a broad but vague team up

As GPU business continues its meteoric rise

The most important company in generative AI proved naysayers wrong

Aims to raise funds to compete with Nvidia

Or about three H100 GPUs

To help fund chip R&D

Could also build custom telecoms, automotive, and video game chips

To help train its Aria generative AI assistant

National Academy of Sciences study comes as Intelligence Community predicts hyperscale-level storage requirements

The third time it has gone to space

Including 340,000 H100 Nvidia GPUs at its data centers

What we can glean from research papers, public comments, and talking to Google Cloud's CEO

Keeping it in the family

A small IT upgrade at Hanscom base