F5 Unlocks Gigascale AI Infrastructure Using NVIDIA BlueField-4 DPUs

F5 BIG-IP Next for Kubernetes with new NVIDIA BlueField-4 DPUs to enhance scalability, security, and performance for next-generation AI workloads

SEATTLE – F5 (NASDAQ: FFIV) today announced expansion of its BIG-IP Next for Kubernetes network and security solution on the newly announced NVIDIA BlueField-4 data processing unit (DPU). This integration of F5 BIG-IP Next for Kubernetes with NVIDIA AI infrastructure is designed to support gigascale AI factories. The combination of these technologies delivers unparalleled AI computing power, intelligent control, advanced security features, and multi-tenant networking at speeds up to 800 Gb/s.

NVIDIA BlueField-4 represents the next frontier in AI infrastructure, empowering enterprises to seamlessly manage token-rich applications, accelerate decision-making processes, and secure data movement at scale. F5 BIG-IP Next for Kubernetes on BlueField-4 enables high-performance traffic management and security for large-scale AI workloads, unlocking rapid token generation, optimized Time to First Token (TTFT), intelligent routing across models, and robust zero-trust architecture for today’s most demanding agentic and autonomous AI systems.

The integration of BIG-IP Next for Kubernetes with NVIDIA BlueField-4 introduces transformative capabilities to AI environments, including:

• Enhanced performance, multi-tenancy, and security: Delivering a +30% improvement in token generation capacity while maintaining cloud-grade expectations.
• Optimized LLM inference via integration with NVIDIA Dynamo and KV Cache Manager: Reducing latency, optimizing GPU utilization, enabling disaggregated serving, and supporting dynamic memory intensity.
• Advanced intelligent routing for AI workloads: Integrating NVIDIA NIM microservices to enable efficient workload allocation across multiple models, ensuring the best possible outcome for customers.
• Granular token governance: Providing crucial visibility into token usage for compliance, accounting, and risk evaluation.
• Scalable and secure Model Context Protocol (MCP): Strengthening protection for MCP-reliant systems while enabling faster AI infrastructure implementation.
• Zero-trust security for VM and bare metal environments: Leveraging the NVIDIA DOCA Platform Framework (DPF) for robust tenant segmentation and secure distributed AI networks.
• Customizable application support: Enabling rapid programmability with F5 iRules tailored for AI-driven workloads and security adaptations.

As autonomous AI agents and agentic systems grow in complexity, the use of AI-driven DPUs has become essential for large-scale AI factories. F5’s platform combined with NVIDIA BlueField-4 unlocks bigger context windows, greater reasoning ability, and sharper situational awareness, laying the technical foundation for the next era of intelligent, goal-driven AI systems.

With F5 BIG-IP Next for Kubernetes working in tandem with NVIDIA BlueField-4, enterprises and cloud-scale operators are better equipped than ever to scale their AI deployments without compromising security or performance. Together, these innovations are shaping the future of gigascale AI factories and autonomous systems. For more information, visit www.f5.com. 

Supporting Quotes

“Organizations worldwide are looking for scalable solutions that can meet the rapidly increasing demands of AI applications while maintaining leading security,” said John Maddison, Chief Marketing Officer at F5. “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.”

“Enterprise AI factories are where intelligence is built, trained, and deployed at unprecedented scale, demanding secure, adaptive, and resilient infrastructure,” said Kevin Deierling, Senior Vice President of Networking at NVIDIA. “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 to help enterprises scale production AI.”