IT之家 · 智能时代T2·68 pts
- The Helion rack is designed specifically for agentic AI workloads, emphasizing flexible CPU/GPU resource composition.
- The pure CPU version, based on sixth-gen EPYC, scales to 32,768 cores per rack, suitable for massive parallel inference.
- AMD plans to contribute the Helion specification to the Open Compute Project (OCP) to drive industry standardization.