Arrcus announced a record 3x increase in bookings in 2025 across datacenter, telco, and enterprise customers, alongside the launch of its Arrcus Inference Network Fabric, a purpose-built networking solution designed to accelerate real-time and agentic AI applications.
The San Jose-based distributed networking infrastructure company said its growth was driven by production deployments of mission-critical switching and routing applications across thousands of network nodes globally. Customers have adopted Arrcus’ ArcOS network operating system and ACE platform across a broad range of open networking hardware, citing flexibility, feature velocity, and reductions in capital and operating costs compared to incumbent networking solutions.
Building on that momentum, Arrcus introduced its Arrcus Inference Network Fabric (AINF), designed to improve the delivery of AI inferencing applications across highly distributed networks. The fabric intelligently steers traffic among inference nodes, caches, and data centers to increase throughput (tokens per second), reduce time to first token, and improve end-to-end latency.
As agentic and physical AI use cases expand, inferencing is expected to become the fastest-growing AI segment. However, enterprises and network operators face challenges around latency, power grid constraints, data sovereignty, model diversity, and cost. Arrcus said traditional hardware-defined networking solutions are not designed to address these distributed, inference-specific demands.
AINF introduces an AI policy-aware network fabric that dynamically routes inference traffic based on operator-defined business policies, including latency targets, data sovereignty boundaries, model preferences, and power constraints. The system evaluates conditions in real time to steer traffic to the optimal node or cache, ensuring the right model is delivered from the appropriate location. Research cited by the company indicates that such innovations can deliver over a 60% reduction in time to first token, a 15% increase in throughput, a 40% reduction in end-to-end latency, and up to a 30% cost reduction.
At its core, AINF includes a policy abstraction layer that translates application intent into infrastructure performance while shielding operators from complexity. Components include query-based inference routing with policy management, interconnect routers, and edge networking. The solution integrates with popular inference frameworks, including vLLM, SGLang, and Triton, and can be deployed with Kubernetes-based orchestration. It also incorporates prefix awareness to optimize key-value cache usage and meet service-level objectives for throughput, latency, sovereignty, power, and cost.
AINF builds on Arrcus’ existing AI and data center networking portfolio, including its ACE-AI solution, which delivers a unified network fabric spanning data centers, the edge, and hybrid cloud environments. The company said AINF supports best-of-breed inferencing xPUs and network silicon from multiple hardware providers and enables partners to integrate load balancers, firewalls, and power management policies to create optimized, secure content delivery networks for inference workloads.
Arrcus also highlighted support and perspectives from industry analysts, customers, and partners across networking and AI infrastructure ecosystems. The company said it will showcase AINF at Mobile World Congress in Barcelona and Nvidia GTC in San Jose.
KEY QUOTES
“To enhance agentic AI adoption by improving response times, networks need to become AI-aware. 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.”
Shekar Ayyar, Chairman and CEO, Arrcus
“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. As inferencing scales across distributed environments, this kind of workload-aware networking will be essential to maximizing AI-enabled application performance.”
Roy Chua, Founder and Principal, AvidThink
“AI Fabrics, scale-up, scale-out, and scale-across, are poised to approach $200B in revenue by 2030 with Ethernet being the major contributor. 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.”
Alan Weckel, Founder and Technology Analyst, 650 Group
“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.”
Scott Raynovich, Founder and Principal Analyst, Futuriom
“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.”
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.”
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’s 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.”
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. 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.”
Mingshou Liu, President, Edgecore Networks
“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.”
Terence Chou, President and CEO, 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. 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.”
Gayathri Radhakrishnan, Partner, Hitachi Ventures
“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.”
Abhishek Shukla, U.S. Managing Director, Prosperity7 Ventures US
