As software development teams are now encouraged to consider the opportunity to embrace AI-first application delivery, API and application delivery controller security management platform company F5 has rolled out a series of advancements designed to underpin developer automation. The company has launched new capabilities for F5 BIG-IP Next for Kubernetes (technology designed to provide networking and security for transitioning complex networks to a cloud-native infrastructure) and also announced a service integrating Red Hat Enterprise Linux with F5 Nginx Plus FIPS compliance functionality.
Accelerated by capitalisation-focused graphical processing unit company Nvidia’s BlueField-3 DPUs (data processing unit, see below), F5 BIG-IP Next for Kubernetes is designed to offer high-performance traffic management and security for large-scale AI infrastructure.
CPU, GPU, what is a DPU?
If central processing units (CPUs) are commonly known as the main “compute engine” powerhouse that sits inside an everyday PC and mobile device, then graphical processing units are of course the super-compute processors originally designed for complex graphical rendering jobs (inside games, video, computer aided design functions and so on) that have been widely reemployed inside cloud platforms due to their parallel processing and parallel calculation abilities.
That leads us to the DPU or data processing unit, a programmable processor that can be described as a system-on-a-chip (SoC) and high-performance network interface capable of parsing, processing and efficiently transferring data at line rate, or the speed of the rest of the network, to GPUs and CPUs. A DPU also features a set of programmable acceleration engines built to offload and improve application performance for AI and machine learning.
Working with DPU power from Nvidia, F5 says it will now offer enhanced performance, multi-tenancy and security to meet cloud-grade expectations. Also here we find integration with Nvidia IDIA Dynamo and KV Cache Manager to reduce latency for the reasoning of large language model (LLM) inference systems and optimisation of GPUs and memory resources. Additionally, we can see smart LLM routing on BlueField DPUs, running effectively with Nvidia NIM microservices for workloads requiring multiple models, providing customers the best of all available models.
Nvidia Dynamo provides a supplementary framework for deploying generative AI and reasoning models in large-scale distributed environments.
The economics of AI
This technology means that “simple AI-related tasks” can be routed to less expensive, lightweight LLMs in supporting generative AI while reserving advanced models for complex queries. This level of customisable intelligence also enables routing functions to use domain-specific LLMs, improving output quality. F5’s traffic management ensures queries are sent to the most suitable LLM, lowering latency and improving time to first token.
“Enterprises are increasingly deploying multiple LLMs to power advanced AI experiences – but routing and classifying LLM traffic can be compute-heavy, degrading performance and user experience,” said Kunal Anand, chief innovation officer at F5. “By programming routing logic directly on Nvidia BlueField-3 DPUs, F5 BIG-IP Next for Kubernetes is the most efficient approach for delivering and securing LLM traffic. This is just the beginning i.e. our platform unlocks new possibilities for AI infrastructure.”
F5 has also worked to now offer a service for Red Hat Enterprise Linux with F5 Nginx Plus FIPS compliance functionality, and this is now available in the AWS Marketplace. Building on the F5 Application Delivery and Security Platform, this technology aims to offer unified application security, scalability and reliability for protecting sensitive data and maintaining compliance with stringent cryptographic standards, including FIPS (Federal Information Processing Standards).
“The F5 solution running on Red Hat Enterprise Linux highlights our ongoing commitment to provide solutions that can help government entities and adjacent organisations extend application and API protections across a growing threat landscape while elevating digital capabilities,” said John Maddison, chief product and corporate marketing officer at F5. “Now available in the AWS Marketplace, customers can seamlessly access this powerful solution as part of the F5 Application Delivery and Security Platform—the first platform that fully converges high-performance load balancing and traffic management with app and API security.”
An enhanced security posture.
These technologies will be of interest to governments and security-first organisations who need enterprise software services to protect and serve application-dependent technologies like AI without compromising security or compliance. The need for governance in this realm is now getting additional exposure and interest due to the rise of platform engineering, as developers are encouraged to tap into the pipeline of self-service automation to a greater degree. The requirement for system-level control through every tier of processing is still fashionable after all.
TOP IMAGE: François Locoh-Donou, president and chief executive officer of F5.