AMD Launches Helion Intelligent AI Rack Solution, Supporting Up to 32,768 CPU Cores per Rack

Beating AI News Flash: AMD today announced the launch of the AMD Helion Intelligent AI Rack Solution, featuring an open infrastructure design based on Open Compute Project (OCP) specifications. The solution is designed to meet the computational demands of large-scale AI agent task execution and supports flexible combinations of CPUs and GPUs. AMD Helion offers two main configurations: 1. A pure CPU rack equipped with 6th Gen AMD EPYC processors, supporting up to 32,768 CPU cores. This configuration is tailored for ultra-large-scale deployments, providing dedicated computational power for agent task execution and connecting to standalone model inference infrastructure. 2. An integrated rack combining AMD EPYC CPUs, AMD Instinct MI350P GPUs, and general-purpose compute nodes, aimed at enterprise-level AI agent applications. AMD stated that Helion supports both liquid cooling and air cooling configurations, allowing customers to adjust CPU and GPU resources based on workload, performance, power consumption, and cost requirements. The solution also incorporates open-source hardware and software along with an integrated Token Router, enabling the allocation of model calls to frontier models and open-source models. AMD plans to submit the Helion specifications to OCP for further development and adoption by the community. Currently, the solution is being co-developed with ecosystem partners and is expected to launch in November 2026.