Purpose-built network fabric designed to accelerate delivery of real-time and agentic AI applications with improved throughput and power efficiency while reducing token retrieval time, latency, and cost per inference.

Arrcus, the leader in distributed networking infrastructure, today announced record 3x bookings growth in 2025 across datacenter, telco and enterprise customers for mission critical switching and routing applications deployed in production across thousands of network nodes globally. Customers have valued the flexibility, innovation and feature velocity of the ArcOS® network operating system and the ACE® platform across a broad range of open networking hardware, along with significant reduction in capital and operating costs compared to alternative incumbent networking solutions. Building on this success, the company also announced its Arrcus Inference Network Fabric (AINF), designed to improve the delivery of inferencing AI applications across a highly distributed network by steering traffic between inferencing nodes, caches, and datacenters with the goal of increasing throughput Tokens per second (TPS), reducing Time to First Token (TTFT), and improving End to End Latency (E2EL) for inferencing.

With the rise of Agentic and Physical AI, Inferencing is expected to be the fastest growing AI segment. However, widespread adoption of Agentic AI is bottlenecked by challenges in the speed of delivery of inference results, diversity in inference models, and bringing smart inference decision making closer to edge nodes. Inferencing infrastructure is deployed in highly distributed clusters, and needs to address the requirements of low latency, availability, constraints in power grid capacity, data sovereignty, and cost. While Enterprises are looking to deploy real-time inferencing so users can have rich localized experiences, Network operators are looking to deliver Inferencing-as-a-service in alignment with the Service Level Objectives (SLO) around these key requirements. To meet these challenges, inferencing infrastructure will require a distributed routing fabric that has granular policy control to intelligently steer traffic and match rapidly evolving requirements. Traditional hardware-defined networking solutions from incumbent vendors fall short in addressing these challenges.

Announced today, the Arrcus Inferencing Network Fabric (AINF) is a purpose-built solution that enables delivery of Inferencing applications with an intelligent ‘AI policy-aware’ network fabric that can dynamically route AI traffic as required between inference nodes, caches, and datacenters to the most appropriate site. Operators can define business policies such as latency targets, data sovereignty boundaries, model preferences, or power constraints. AINF enables evaluation of these conditions in real time to steer inference traffic to the optimal node or cache, ensuring the right model is delivered from the right location at the right time. Research¹ shows that such innovation in AI infrastructure can deliver over 60% reduction in TTFT, 15% TPS improvement, 40% E2EL and up to 30% cost reduction.

“To enhance agentic AI adoption by improving response times, networks need to become AI-aware,” said Shekar Ayyar, Chairman and CEO of Arrcus. “AINF extends Arrcus’ leadership in distributed networking by delivering the first fabric designed to meet the latency, sovereignty, and power constraints of large-scale AI inferencing.”

At its core, AINF introduces a policy abstraction layer that translates the inferencing application intent to underlying infrastructure performance, while shielding operators from infrastructure complexity. AINF components include query-based inference routing with policy management, interconnect routers, and edge networking. AINF is designed to integrate with popular inference frameworks including vLLM, SGLang, Triton, and others, thus coupling optimal model selection with a high performance steering fabric. Using Kubernetes-based orchestration AINF can be composed and deployed in an automated manner. Concepts like prefix awareness to optimize KV cache usage enable inferencing applications to meet SLO for throughput, token retrieval time, latency, data sovereignty, power and cost.

AINF builds on Arrcus’ proven leadership in AI and Datacenter Networking, with its ACE-AI solution already delivering a unified network fabric for distributed AI spanning datacenters, edge and hybrid cloud environments with scale-out and scale-across solutions. As with all Arrcus solutions, AINF has the unique capability of working with best of breed inferencing xPUs and network silicon across hardware providers. It is also designed to allow partner companies to bring in their load balancers, firewalls, and power management policies to create optimal caching and secure CDNs for superior inference results.

Analyst Perspectives

“Traditional network fabrics weren't designed with AI inference workloads in mind. Arrcus' Inference Network Fabric changes that with a policy-aware, intent-driven approach that understands inference-specific demands — latency sensitivity, model selection, cache optimization — and dynamically routes traffic accordingly,” said Roy Chua, Founder and Principal, AvidThink. “As inferencing scales across distributed environments, this kind of workload-aware networking will be essential to maximizing AI-enabled application performance.”

“AI fabrics, scale-up, scale-out, and scale-across are poised to approach $200B in revenue by 2030 with Ethernet being the major contributor,” said Alan Weckel, Founder and Technology Analyst at 650 Group. “Network fabrics can significantly improve AI fabric performance and help customers scale the network with the rapid growth in accelerators as the market moves from foundational model training to inference being the dominant use case.”

“With its efficient distributed cloud networking platform and newly announced Arrcus Inferencing Network Fabric (AINF), Arrcus is well-positioned to serve diverse networking needs across industries, providing scalable and high-performance connectivity for any application ranging from communications services to AI inference,” said Scott Raynovich, Founder and Principal Analyst, Futuriom.

Customer and Partner Perspectives

“We are pleased to see Arrcus’ continued innovation in AI networking software, powered by Broadcom’s high-density, high-performance networking portfolio,” said Hasan Siraj, vice president of product management, Core Switching Group, Broadcom. “Broadcom is leading the AI networking infrastructure revolution with industry-defining platforms based on our Tomahawk, Jericho, and Thor Ultra product lines. We look forward to deepening our collaboration with Arrcus as AINF leverages Broadcom’s platforms to deliver next-generation AI networks at scale.”

“As AI inferencing scales across distributed environments, the network fabric becomes critical to performance and economics. Lightstorm is building hyperscaler-grade backbone infrastructure across APAC to support these demanding workloads. We see strong alignment with Arrcus' vision for intelligent, policy-aware networking that addresses real-world constraints of latency, sovereignty, and power efficiency,” said Amajit Gupta, Group CEO & MD, Lightstorm.

“As Arrcus’ strategic partner, I am really excited about the announcement of the Arrcus Inference Network Fabric (AINF), which we are confident will significantly transform the future of AI inferencing,” said Masaaki Moribayashi, Corporate Executive Officer, SEVP, Head of Network & Data Center Business Group, Fujitsu Limited, Representative Director, CEO, 1Finity Inc.

“UfiSpace is proud to support Arrcus’ momentum in the AI market. By providing the open hardware foundation for the Arrcus Inference Network Fabric (AINF), we are empowering our joint customers to solve the critical power and latency constraints of distributed inference. Together, we are delivering a solution that is not only scalable and cost-effective but fully ready for the demands of next-generation AI workloads,” said Vincent Ho, Chairman and CEO, UfiSpace.

“We are excited to see Arrcus pushing the boundaries of high-performance AI inferencing connectivity with AINF. As the world’s leading provider of white-box switching solutions, Edgecore is committed to delivering the highest-performance hardware platforms that enable intelligent, AI-aware networking at scale,” said Mingshou Liu, President of Edgecore Networks. “As AI inferencing architectures move beyond 800 Gbps line rates and demand deterministically low latency, the network becomes a critical accelerator of innovation and cost-effectiveness. Intelligent traffic management is no longer optional — it is foundational to unlocking the next generation of AI infrastructure.”

“Arrcus’ purpose-built network fabric collaborates with partner companies’ network solutions to deliver AI-Policy-Aware, autonomous optimization for scale-up and scale-out AI Inference results. Accelerating AI Inference at Edge and the new concept of AI Grid connecting AI Factories are the foundation to promote AI Inference everywhere. I am confident, and Lanner will work with Arrcus together on transforming AI infrastructure toward AI Inference everywhere,” said Terence Chou, President and CEO of Lanner.

“As AI shifts from centralized training to globally distributed inference, the network layer is no longer just operational but also a strategic control point,” said Gayathri Radhakrishnan, Partner, Hitachi Ventures. “Incumbent rigid networks pose major constraints that Arrcus is eliminating with AINF — a smart layer where policy, economics, and infrastructure realities including power availability determine how AI scales efficiently across datacenter, edge, and sovereign environments.”

“As organizations across enterprise, telecommunications, and public-sector environments build AI capabilities, the ability to deliver inference with performance, governance, and efficiency becomes critical. Arrcus’ AINF addresses this emerging need by enabling intelligent, distributed networking tailored for modern AI workloads. We’re proud to support Arrcus as they help shape this next generation of AI infrastructure,” said Abhishek Shukla, U.S. Managing Director at Prosperity7 Ventures US.

Visit the Arrcus website for more information and contact us on how you can get started today with AINF to improve your inferencing results. Meet with Arrcus at MWC in Barcelona as well as Nvidia GTC in San Jose.

Additional Resources

• Fujitsu, 1Finity and Arrcus sign strategic partnership agreement to deliver innovative network solutions for AI infrastructure
• Arrcus ArcOS and Broadcom Jericho2 enable Softbank Corp. to Successfully Provide World’s First Services on 5G Commercial Network
• Arrcus welcomes Broadcom’s Thor Ultra: Industry’s First 800G AI Ethernet NIC
• Arrcus Harnesses NVIDIA BlueField-4 to Power Gigascale AI Factories with Superior Network Performance and Efficiency
• Anyscale Ray Serve: Reduce LLM Inference Latency by 60% with Custom Request Routing
• vLLM Semantic Router: Improving efficiency in AI reasoning
• Multi-LLM routing strategies for generative AI applications on AWS

About Arrcus

Arrcus is a leading provider of networking software solutions that enable organizations to achieve unmatched scalability, performance, and reliability across their infrastructure. The company is transforming the industry with disaggregated solutions that deliver innovative, agile, and cost-effective networking, empowering businesses to move beyond traditional, monolithic systems and adopt a more flexible, efficient, and scalable approach to modern connectivity.

Arrcus’ team includes world-class technologists with an exceptional track record in delivering industry-leading networking products, alongside recognized specialists, operating executives, strategic partners, and top-tier venture capital investors. The company is headquartered in San Jose, California. For more information, visit the official website or follow Arrcus on LinkedIn and Twitter/X.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260217706207/en/

“AINF extends Arrcus’ leadership in distributed networking by delivering the first fabric designed to meet the latency, sovereignty, and power constraints of large-scale AI inferencing,” said Shekar Ayyar, Chairman and CEO of Arrcus.