ASUS released the XA P2N - E2 equipped with NVIDIA Vera CPU on OCP 2026, targeting Agentic AI workloads.
Provides a unified AI infrastructure blueprint that covers computing, networking, memory, and storage.
San Jose, California, USA, October 12th / PRNewswire / -- ASUS is expanding its AI infrastructure product portfolio by introducing the XA P2N - E2. This is a server based on a 2U NVIDIA MGX architecture, equipped with NVIDIA Vera CPU, and is designed for agentic AI workloads as well as reinforcement learning tasks. The server was unveiled in OCP Global Summit 2026, aiming to serve as the execution layer for AI applications, handling tasks such as code execution, tool usage, sandboxes, data processing, and orchestration that go beyond the AI of the models themselves. XA P2N - E2 supports up to two dual-width NVIDIA RTX PRO 6000 Blackwell Server Edition GPU, combining high-performance CPU computing with flexible GPU acceleration in a compact 2U platform. ASUS states that the high single-thread CPU performance, high bandwidth, and energy-efficient memory are designed to ensure that the AI agent remains responsive during intensive execution and evaluation tasks.
At OCP, ASUS also showcased a broader product portfolio, covering rack-level AI systems, accelerated computing, high-speed networking, context memory, low-latency inference, and high-density storage. At the rack level, XA VR721 to E3 and ASUS AI POD integrate 36 NVIDIA Vera CPU and 72 NVIDIA Rubin GPU through the NVIDIA Vera Rubin NVL72 platform, and adopt a fully liquid-cooled architecture for large-scale AI training, post-training, and inference. For more flexible server configurations, XR R1I12B to M1BHFS combine with NVIDIA HGX Rubin NVL8; they use direct-contact chip liquid cooling for the GPU chassis and air cooling for the Intel ® Xeon ® 6 processors. ASUS stated that these systems reflect their approach to scaling AI infrastructure across different computing densities, cooling architectures, and deployment requirements, covering everything from single servers to large-scale AI environments.
Build a complete AI factory based on the NVIDIA Vera Rubin platform.
Asus is expanding its product portfolio based on NVIDIA acceleration, covering system-level and rack-level architectures, enabling customers to scale computing density, cooling, and deployment modes according to workload requirements. Asus states that the performance of AI factories increasingly depends not only on accelerated computing. High-speed networks, scalable context memory, responsive inference, and data infrastructure are all key to maintaining efficient data transmission and workload performance in the increasingly complex AI environment.
In addition to the hardware stack, NVIDIA DSX, NVIDIA Omniverse DSX Blueprint, for, and AI Factory Digital Twins were also showcased at the ASUS booth. They are part of NVIDIA DSX Sim and combine a verified architecture with high-fidelity simulation, enabling a physically accurate digital twin to optimize the design and operation of AI factories before deployment.
The four NVIDIA technologies displayed at ASUS's booth integrate the key elements of the next-generation AI infrastructure. NVIDIA HGX Rubin NVL8 provides accelerated computing, combined with Ethernet switches based on NVIDIA Spectrum - X Spectrum -6 to achieve high-speed AI networks. NVIDIA CMX Context Memory Storage Platform offers scalable context memory, while NVIDIA Groq 3 LPX is an interactive AI inference accelerator designed for NVIDIA Vera Rubin NVL72.
To meet the requirements of the agentic system for low latency and large context, NVIDIA Groq 3 LPX generates extended NVIDIA Vera Rubin NVL72 through ultra-fast token to achieve highly responsive inference. ASUS states that these systems collectively reflect its approach to building scalable AI factories based on the NVIDIA Vera Rubin platform, which involves integrating standardized, modular infrastructure into computing, networking, context memory, inference, and storage. This full-stack architecture enables customers to scale from a single system to rack-level deployments, while optimizing performance per watt and accelerating time to market.
Agentic AI server equipped with Intel Xeon 6 processors breaks through performance boundaries
The independent Intel and AMD display areas further enhance the capabilities of the ASUS platform, allowing customers to choose the appropriate architecture based on different needs such as cloud computing, AI, and high-performance computing.
The Intel exhibition area showcases RS700-E12-RS4U and RS720-E12-RS12U. These two products utilize 1U and 2U dual-platform designs, respectively, and are equipped with Intel Xeon processors. Their DC-MHS design, along with tool-free maintenance features, support modular deployment and simplified maintenance. They also offer flexible storage and expansion options, making them suitable for agentic, AI, virtualization, and data-intensive workloads.
Leveraging AMD EPYC 9006 and Instinct platforms to expand architectural options
The exhibition area has launched the ASUS RS700A-E14B-R16U, equipped with the sixth-generation AMD EPYC 9006 series processor, codenamed “Venice”. This 1U dual-socket platform is designed for enterprise-level resilience, combining DC-MHS architecture, PCIe ® 6.0 connectivity, and support for up to 16 E3.S hard drives to meet the needs of compute-intensive and data-intensive infrastructure. As a complement to high-density designs, the ASUS Thermal Radar 3.0 provides advanced thermal monitoring and management to optimize air cooling efficiency, helping the system maintain stability and performance under high loads, while also improving overall data center thermal management.
In terms of acceleration, ASUS ESC8000A-E13P supports AMD Instinct MI350P PCIe graphics cards, while XA AM3A to E13 integrate 8 AMD Instinct MI355X accelerators in their 10U design. This solution allows for both CPU and GPU to use air cooling, eliminating the need for dedicated chilled water infrastructure to achieve high-density AI deployment. It maintains scalability and maintainability, while providing greater flexibility for deploying high-demanding AI and HPC workloads.
Asus stated that in OCP Global Summit 2026, the company will combine system-level and rack-level engineering, accelerated computing, networking, and storage with leading technology platforms to provide flexible infrastructure for a wide range of AI, cloud, and HPC workloads. This integrated product portfolio enables organizations to adjust their computing architecture, data infrastructure, and deployment models according to changing performance and scalability requirements.
Visitors can go to the ASUS booth # B9 during OCP Global Summit 2026 to experience the complete portfolio of ASUS AI infrastructure products.
Supply and Pricing
ASUS servers are available for purchase worldwide. The availability of various products and configurations may vary by region. For more details, please contact your local ASUS representative.
