.jpg)
The demands of gigascale AI factories require a new approach to networking and security that can operate at unprecedented speeds and scales. F5 has announced the expansion of its BIG-IP Next for Kubernetes solution onto the newly launched NVIDIA BlueField-4 data processing unit (DPU). This integration is designed to support next-generation AI workloads by delivering intelligent control, advanced security, and multi-tenant networking at speeds up to 800 Gb/s, unlocking unparalleled AI computing power.
F5 integrates its BIG-IP Next for Kubernetes with the new NVIDIA BlueField-4 DPU.
The solution is designed for gigascale AI factories, supporting speeds up to 800 Gb/s.
It delivers a 30% improvement in token generation capacity.
Features include optimized LLM inference and intelligent routing for NVIDIA NIM microservices.
It provides granular token governance and scalable, secure Model Context Protocol (MCP) support.
The integration enables zero-trust security for VM and bare metal AI environments.
The integration introduces several key capabilities critical for large-scale AI. It enhances performance and multi-tenancy, improving token generation capacity by over 30%. It optimizes LLM inference by integrating with NVIDIA Dynamo and KV Cache Manager to reduce latency and optimize GPU utilization. The solution also provides advanced intelligent routing to efficiently allocate workloads across multiple AI models and offers granular token governance for compliance and risk evaluation.
John Maddison, Chief Marketing Officer at F5, highlighted the market need, stating, “Organizations worldwide are looking for scalable solutions that can meet the rapidly increasing demands of AI applications while maintaining leading security. The integration of BIG-IP Next for Kubernetes with NVIDIA BlueField-4 DPUs delivers unmatched performance and reliability, helping enterprises build AI-driven systems that respond smarter, faster, and more securely.”
Kevin Deierling, Senior Vice President of Networking at NVIDIA, emphasized the infrastructure demands, saying, “Enterprise AI factories are where intelligence is built, trained, and deployed at unprecedented scale, demanding secure, adaptive, and resilient infrastructure. Combined with NVIDIA BlueField-4, F5 BIG-IP Next for Kubernetes provides intelligent AI application delivery and security that supports token processing with trust and precision.”
As autonomous AI agents grow in complexity, the use of AI-driven DPUs has become essential. The combination of F5's platform with BlueField-4 unlocks bigger context windows, greater reasoning ability, and sharper situational awareness for AI systems. It also provides a scalable and secure framework for the Model Context Protocol (MCP) and leverages the NVIDIA DOCA framework for robust zero-trust security in distributed AI networks.
This collaboration provides a critical piece of the gigascale AI puzzle. By offloading and accelerating networking and security functions to the DPU, F5 and NVIDIA are enabling enterprises to scale their AI deployments without compromising on the performance or security required for the most demanding agentic and autonomous AI systems.
F5, Inc. is the global leader that delivers and secures every app. Backed by three decades of expertise, F5 has built the industry’s premier platform—F5 Application Delivery and Security Platform (ADSP)—to deliver and secure every app, every API, anywhere: on-premises, in the cloud, at the edge, and across hybrid, multicloud environments. F5 is committed to innovating and partnering with the world’s largest and most advanced organizations to deliver fast, available, and secure digital experiences. Together, we help each other thrive and bring a better digital world to life.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.