THE CRUNCH
ASUS has announced the XA P2N-E2, a 2U server built on NVIDIA's MGX architecture and powered by NVIDIA Vera CPUs, unveiled at the OCP Global Summit 2026. The company positions it for agentic AI and reinforcement learning workloads, specifically the execution layer of AI applications: code execution, tool use, sandboxing, data processing and orchestration that sit beyond the AI model itself. The platform supports up to two dual-slot NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, and ASUS says high single-thread CPU performance and energy-efficient memory are intended to keep AI agents responsive during demanding execution and evaluation tasks.
The announcement, carried as a press release rather than independent reporting, sits within a broader ASUS showcase at OCP. At rack scale, the XA VR721-E3 AI POD integrates 36 NVIDIA Vera CPUs and 72 NVIDIA Rubin GPUs through the Vera Rubin NVL72 platform in a fully liquid-cooled design, while the XR R1I12B-M1BHFS pairs NVIDIA HGX Rubin NVL8 with direct-to-chip liquid cooling for the GPU baseboard and air cooling for Intel Xeon 6 processors.
ASUS also showed Intel Xeon 6 and AMD EPYC 9006-based servers at the event, alongside NVIDIA networking, context memory and inference technologies, framing the portfolio as options across different compute densities, cooling architectures and deployment scales.