Microsoft’s Maia 300 Chip Promises 40 Percent More AI Output per MW
Scott Guthrie, executive vice president of Cloud and AI, said in a blog post that the company intends to scale the Azure Maia family to multi-gigawatt deployments.
Inference is the stage at which trained artificial intelligence models produce answers to user requests.
Microsoft projects that Maia 300 will generate 40% more tokens per megawatt than leading systems built on graphics processing units. According to the company, a 96-accelerator configuration can reach up to seven times the rack-level token throughput of Maia 200.
Production rollouts of Maia 300 are slated to start in 2027.
Its predecessor, Maia 200, already powers production workloads including Microsoft Copilot. GitHub Copilot and Microsoft Foundry are due to follow by the end of the year.
Microsoft said the new system is built for long-context reasoning, time-sensitive conversations and multistep AI agent tasks.
Legal Disclaimer:
MENAFN provides the
information “as is” without warranty of any kind. We do not accept
any responsibility or liability for the accuracy, content, images,
videos, licenses, completeness, legality, or reliability of the information
contained in this article. If you have any complaints or copyright
issues related to this article, kindly contact the provider above.
Legal Disclaimer:
EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.
