SoftBank Announces Infrinia AI Cloud OS

By

The software stack was designed to maximize GPU performance.

SoftBank has announced Infrinia AI Cloud OS, “a software stack for AI data centers that manages GPUs, Kubernetes, and AI workloads at scale.”

Building and operating GPU cloud services requires highly specialized expertise and involves complex operational tasks, the announcement states. To address these challenges, the software stack was designed to “maximize GPU performance while enabling the easy and rapid deployment and operation of advanced GPU cloud services.”

With Infrinia AI Cloud OS, operators “can build Kubernetes as a Service (KaaS) in a multi-tenant environment, and Inference as a Service (Inf-aaS) that provides Large Language Model inference capabilities via APIs, as part of their own GPU cloud services,” the announcement says.

For more information, visit Infrinia.ai to sign up for the public preview.
 
 

 
 
 

02/02/2026
data center , HPC , Performance

Related content

comments powered by Disqus