Powered by MOMENTUMMEDIA
For breaking news and daily updates, subscribe to our newsletter

Equinix, NVIDIA, and Together AI target distributed enterprise inference

Equinix is expanding its collaboration with NVIDIA and partnering with Together AI to launch a distributed AI inference program aimed at helping enterprises deploy workloads closer to their data, users, and applications.

Equinix, NVIDIA, and Together AI target distributed enterprise inference

Equinix has announced the Equinix Inference Exchange, a distributed AI inference program being developed with NVIDIA and Together AI.

The offering will combine NVIDIA’s Enterprise Reference Architectures with Together AI’s inference platform, which supports more than 200 open-source models, and Equinix’s global data centre and interconnection infrastructure.

The companies said the approach is designed to give enterprises greater flexibility over where AI inference runs while addressing performance, cost and governance requirements.

 
 

“AI is transforming enterprise technology at extraordinary speed, and the infrastructure decisions enterprises make today will define their competitive position for years to come,” Adaire Fox-Martin (pictured), CEO and president of Equinix, said in a statement.

Fox-Martin said Equinix’s relationship with NVIDIA provides the accelerated computing foundation for the offering, while Together AI’s open-model approach will give enterprises greater choice over how they scale AI workloads.

NVIDIA vice president of global AI clouds and infrastructure ecosystem Raj Mirpuri added that the exchange would allow enterprises to bring AI inference closer to their data, applications, and customers.

The program will use Equinix Fabric to connect inference providers with clouds, networks, and AI providers across major metropolitan areas, potentially reducing latency and deployment complexity.

The Inference Exchange will combine Equinix infrastructure and operations with NVIDIA’s AI infrastructure and Together AI’s inference platform. Together AI will support both multitenant environments and dedicated single-tenant deployments for organisations requiring dedicated capacity.

Together AI CEO Vipul Ved Prakash said the collaboration demonstrates that model choice and performance do not have to be trade-offs for enterprises.

Equinix Inference Exchange is scheduled to become available in the first quarter of 2027.

Cyber DailyWant to see more stories from trusted news sources?
Make Cyber Daily a preferred news source on Google.
Tags: