NVIDIA and Cisco have announced plans to develop Ultra-Dense Small Form Factor Pluggable (USFP), a high-density optical module designed to support the next generation of AI factories using pluggable transceivers.
The new technology is designed to deliver 400Gb/s per lane, enabling AI infrastructure operators to connect more computing systems while managing network complexity, power consumption and costs as AI models and inference workloads continue to expand.
USFP aims to improve data transfer efficiency across AI Ethernet fabrics while extending a deployment model already proven across multiple generations of data centre networks. The technology is intended to help customers adopt next-generation optical connectivity without requiring major changes to existing data centre infrastructure.
Comparable in size to an OSFP module, USFP delivers four times the bandwidth and front-panel bandwidth density, alongside approximately 1.3 times the power efficiency compared with 200Gb/s-per-lane pluggable modules.
The higher bandwidth density is expected to allow AI builders to increase computing capacity within the same network footprint while reducing networking’s share of the overall AI factory power budget.
Gilad Shainer, Senior Vice President at NVIDIA, said the collaboration focuses on rethinking connectivity to support larger AI factories. He said USFP would help create an ecosystem for higher-density and more efficient pluggable optics.
Bill Gartner, Senior Vice President and General Manager of Optical Systems and Optics at Cisco, said the architecture is designed to scale performance while maintaining serviceability, deployment flexibility and operational simplicity.
NVIDIA and Cisco are working with TE Connectivity and Amphenol to develop USFP cages, connectors and modules. Additional partners are expected to join the initiative, with the shared form factor providing suppliers with a common foundation for developing high-density infrastructure for 400Gb/s-per-lane fabrics.
The collaboration also builds on existing work to ensure NVIDIA Spectrum-X Ethernet networking and Cisco Silicon One-based Ethernet networks operate together. The integration is intended to simplify AI infrastructure deployment for enterprises, neoclouds and sovereign clouds.
NVIDIA and Cisco plan to establish an open industry specification for USFP through an upcoming community-led multi-source project, allowing wider industry participation in developing the technology.
