F5 and Intel combine to shape AI service security and delivery

F5 is combining its NGINX Plus and the Intel Distribution of OpenVINO toolkit and infrastructure processing units (IPUs) to deliver protection, scalability, and performance for advanced AI inference.

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.

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

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

The F5-Intel collaboration excels in edge computing scenarios, particularly for video analytics and IoT applications that demand minimal latency and peak performance. Deploying NGINX Plus on Intel’s IPU enables swift and dependable responses, making this solution well-suited for content delivery networks and distributed microservices architectures

“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 of 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,” said Pere Monclus, Chief Technology Officer of Network and Edge Group at Intel.