Microsoft adds remote AI inference tools for robots

Image: Primary

Published Wednesday, September 23, 2026 · 1:07 PM EDT

Microsoft Research has added remote AI inference support to its Physical AI Toolchain, allowing developers to distribute robot workloads across onboard computers, nearby servers and cloud GPUs. The release includes example projects for SO-101 and UR10e robots and uses Kubernetes to package and place the workloads. In Microsoft's tests of mobile robot tasks, shifting computation away from onboard GPUs improved response time and accuracy while reducing battery drain. The approach can also let robots use larger models than their onboard hardware can hold. Its benefit depends on network latency, bandwidth and access to remote GPUs, which can constrain robots working in unpredictable environments.

Sources

Microsoft Research

In this story

Microsoft

Published by Tech & Business, a media brand covering technology and business. This story was sourced from Microsoft Research and reviewed by the T&B editorial agent team.

Back to Newswire

Keep reading

Full wire

AI Infrastructure

Nvidia releases Reshard implementation to speed reinforcement learning weight transfers

Nvidia has made an open source implementation of Reshard available to transfer updated model weights between training and inference GPUs. The company reports speedups of 2.7x to 5.7x over conventional gather-and-broadcast transfers in NeMo RL benchmarks.

Infrastructure AI

TSMC considers expanding into advanced memory manufacturing

Taiwan Semiconductor Manufacturing Co. is considering adding advanced memory chip manufacturing to its business, The Information reported. Such an expansion would give the world's largest chipmaker a bigger share of the AI hardware supply chain.

AI Infrastructure

Musk says government work will fall below 10% of SpaceX revenue

Elon Musk said government contracts will account for less than 10% of SpaceX revenue this quarter, down from 16.6% in the third quarter, The Next Web reports. Renting AI computing has become its largest revenue source.

AI Infrastructure

Nvidia reports faster FLUX 3 image generation with VisualGen optimizations

Nvidia reported that combined runtime optimizations accelerated FLUX 3 Image Klein Base image generation on a single B200 GPU.

AI Infrastructure

Vercel adds DeepSeek search and page retrieval to AI Gateway

Vercel announced that DeepSeek Search and DeepSeek Fetch are available through AI Gateway for any model that supports tool calling. Developers can use one Gateway API key without creating a separate DeepSeek account and retain the tools when switching model providers.

Infrastructure AI

AWS adds amortized cost reporting for reserved GPU capacity

AWS now spreads the upfront cost of EC2 Capacity Blocks for ML across each reservation's duration in Cost Explorer and its Cost and Usage Report 2.0. Customers can see costs assigned to instances that used the reservation and costs attributable to unused capacity.