F5 and Intel collaboration simplifies the security and delivery of AI services

1 min read

F5 has announced that it is bringing application security and delivery capabilities to AI deployments powered by Intel.

Credit: Sutthiphong - adobe.stock.com

This is a new joint solution that combines security and traffic management from F5’s NGINX Plus offering with the optimisation and performance of the Intel Distribution of OpenVINO toolkit and Infrastructure Processing Units (IPUs) providing improved levels of protection, scalability, and performance for advanced AI inference.

With more organisations adopting AI to power intelligent applications and workflows, efficient and secure AI inference is becoming more critical.

This is addressed by combining the OpenVINO toolkit - which optimises and accelerates AI model inference - with F5 NGINX Plus, providing both traffic management and security.

The OpenVINO toolkit simplifies the optimisation of models from almost any framework to enable a write-once, deploy-anywhere approach and enables developers to create scalable and efficient AI solutions with minimal code changes.

F5 NGINX Plus enhances the security and reliability of these AI models. Acting as a reverse proxy, NGINX Plus manages traffic, ensures high availability, and provides active health checks. It also facilitates SSL termination and mTLS encryption, safeguarding communications between applications and AI models without compromising on performance.

To further boost performance, Intel IPUs offload infrastructure services from the host CPU, freeing up resources for AI model servers. The IPUs are able to efficiently manage infrastructure tasks, opening up resources to enhance the scalability and performance of both NGINX Plus and OpenVINO Model Servers (OVMS).

This integrated solution is seen as being beneficial for edge applications, such as video analytics and IoT, where low latency and high performance are crucial. By running NGINX Plus on the Intel IPU, the solution ensures rapid and reliable responses, making it suitable for content delivery networks and distributed microservices deployments.

“Teaming up with Intel empowers us to push the boundaries of AI deployment. This collaboration highlights our commitment to driving innovation and delivers a secure, reliable, and scalable AI inference solution that will enable enterprises to securely deliver AI services at speed.

“Our combined solution ensures that organisations can harness the power of AI with superior performance and security,” said Kunal Anand, Chief Technology Officer at F5.

“Leveraging the cutting-edge infrastructure acceleration of Intel IPUs and the OpenVINO toolkit alongside F5 NGINX Plus can help enable enterprises to realise innovative AI inference solutions with improved simplicity, security, and performance at scale for multiple vertical markets and workloads,” added Pere Monclus, Chief Technology Officer, Network and Edge Group of Intel.

The solution is now available.