Microsoft announces powerful new chip for AI inference

Microsoft announces powerful new chip for AI inference

Microsoft has announced the launch of its latest chip, the Maia 200, which the company describes as a silicon workhorse designed for scaling AI inference.

The 200, which follows the company’s Maia 100 launched in 2023, has been technically outfitted to run powerful AI fashions at sooner speeds and with more effectivity, the company has said. Maia comes geared up with over 100 billion transistors, delivering over 10 petaflops in 4-bit precision and roughly 5 petaflops of 8-bit performance—a considerable enhance over its predecessor.

Inference refers to the computing means of working a mannequin, in distinction with the compute required to coach it. As AI corporations mature, inference prices have turn out to be an more and more important a part of their general working value, resulting in renewed curiosity in methods to optimize the course of.

Microsoft is hoping that the Maia 200 may be a part of that optimization, making AI companies run with less disruption and decrease energy use. “In practical terms, one Maia 200 node can effortlessly run today’s largest models, with plenty of headroom for even bigger models in the future,” the company said.

Microsoft’s new chip is also a part of a rising development of tech giants turning to self-designed chips as a strategy to reduce their dependence on NVIDIA, whose cutting-edge GPUs have turn out to be more and more pivotal to AI corporations’ success. Google, for occasion, has its TPU, the tensor processing models—which aren’t bought as chips however as compute energy made accessible by way of its cloud. Then there’s Amazon Trainium, the e-commerce big’s personal AI accelerator chip, which just launched its latest version, the Trainium3, in December. In each case, the TPUs can be utilized to dump some of the compute that would in any other case be assigned to NVIDIA GPUs, lessening the general {hardware} value.

With Maia, Microsoft is positioning itself to compete with those alternate options. In its press release Monday, the company famous that Maia delivers 3x the FP4 performance of third era Amazon Trainium chips, and FP8 performance above Google’s seventh era TPU.

Microsoft says that Maia is already laborious at work fueling the company’s AI fashions from its Superintelligence team. It has also been supporting the operations of Copilot, its chatbot. As of Monday, the company said it has invited a wide range of events — including builders, lecturers, and frontier AI labs — to make use of its Maia 200 software development equipment of their workloads.

The Gossip Blogger event

San Francisco
|
October 13-15, 2026

Stay informed with the latest headlines that matter. At TheGossipBlogger.com, we ship well timed and credible coverage on breaking news, global occasions, politics, society, and every thing in between.

Whether it’s unfolding developments, coverage modifications, or powerful human-interest tales, our newsroom curates impactful content to maintain you up to date in real time.

From local points to worldwide affairs, we break down advanced tales with readability, context, and a deal with what’s related to you.

Bookmark News and test in often — because staying informed is the first step towards staying ahead.