AMD introduced the AMD Helion agentic AI rack, an open blueprint for agentic AI infrastructure based on an Open Compute Project spec-design and powered by AMD compute.
Building on the open-platform approach of the AMD Helios rackscale solution, AMD Helion gives partners and customers the flexibility they need for agentic AI infrastructure. With AMD Helion, customers can match CPU performance, core density and power with GPU acceleration for the work their AI agents perform.
“Agentic AI is not a single workload. It spans personal agents, enterprise applications, code execution and complex workflows, each with different compute requirements,” said Dan McNamara, senior vice president and general manager, Compute and Enterprise AI, AMD. “To do that takes optimized compute and infrastructure that can adapt to different workloads. With AMD Helion, we are bringing AMD EPYC™ performance, open software and flexible rack designs together so our partners can build systems around customer needs and make efficient use of available power.”
AMD Helion’s OCP spec-based rack blueprint supports open software and comes in flexible configurations, including liquid- and air-cooled versions, allowing customers to create virtually any configuration they need. Some examples of this include:
- A CPU-only rack powered by 6th Gen AMD EPYC processors that can support up to 32,768 CPU cores. This rack is designed for hyperscale customers, providing dedicated capacity for agent execution and connections to separate model inference infrastructure.
- An all-in-one rack that combines AMD EPYC CPU nodes, AMD Instinct MI350P GPU nodes and general-purpose compute on one platform. This rack is designed to provide partners and customers with an all-in-one concept for enterprise agentic AI.
AMD Helion lets customers deploy agentic AI in their existing IT infrastructure, turning existing investments into a foundation for new AI capabilities. Partners can tailor CPU and GPU configurations to customer workloads, matching agent execution, model inference and supporting compute to each deployment’s performance, power and cost requirements.
AMD plans to contribute the AMD Helion specification to OCP, making it available to the community for further development and adoption. AMD Helion agentic rack configurations are currently under development with ecosystem partners and are planned to be available in November 2026.
AMD is helping shape the next phase of AI infrastructure through open, flexible platforms, a broad portfolio of workload-optimized compute and collaboration across the ecosystem. AMD Helion brings that approach to agentic AI, helping partners match software and compute to the work agents perform and giving customers flexibility to scale as their requirements evolve.
