![](\"https:\/\/mms.businesswire.com\/media\/20260602141542\/en\/2822229\/5\/Ayar_Labs_Final_RGB.jpg\")
<\/a><\/a>\nAs AI factories scale to larger GPU counts and increasingly heterogeneous architectures, data movement and power are turning into critical bottlenecks. System designers must rethink how compute elements are connected, how bandwidth scales over distance, and how power is allocated across the rack.<\/p>
\nAyar Labs\u2019 CPO solution is designed to address scaling limits by bringing high-bandwidth, low-latency, power-efficient connectivity to NVLink Fusion architectures, helping customers expand design headroom as bandwidth requirements grow and electrical constraints tighten. By putting optics where it matters most, Ayar Labs\u2019 CPO enables flexible system architectures and efficient AI scaling beyond the limits of copper.<\/p>
\n\u201cAI infrastructure is being co-designed from the ground up, and customers need more options to scale performance efficiently as bandwidth continues to rise,\u201d said Mark Wade, CEO at Ayar Labs. \u201cBy joining the NVIDIA NVLink Fusion ecosystem, we\u2019re introducing co-packaged optics as a foundational building block for customers deploying heterogeneous compute in NVIDIA AI factories.\u201d<\/p>
\n\u201cNVLink Fusion, combined with Ayar Labs\u2019 CPO technology, gives customers more options to build heterogeneous AI factories,\u201d said Ashish Karandikar, Vice President at NVIDIA. \u201cBy expanding the NVLink Fusion ecosystem with Ayar Labs\u2019 optical connectivity, innovators can scale bandwidth and bring heterogeneous AI infrastructure to market faster.\u201d<\/p>
\nThe collaboration is designed to help customers deploy heterogeneous compute, including custom silicon, within NVIDIA rack-scale platforms while preserving NVLink-based architecture investments. NVLink Fusion provides a path for integrating custom CPUs and XPUs into NVIDIA\u2019s rack-scale architecture and ecosystem, enabling customers to move faster from system concept to deployment at scale.<\/p>
\nAyar Labs\u2019 CPO solutions complement NVIDIA\u2019s broader AI factory stack by pairing NVLink Fusion with NVIDIA\u2019s end-to-end networking platform. Together, these technologies support next-generation AI factories as they scale within and across racks, where bandwidth density, latency, and power efficiency directly impact utilization and total cost of ownership.<\/p>
\nAyar Labs will work with customers and ecosystem partners to align CPO integration with NVLink Fusion deployments, including system architecture, validation requirements, and platform timelines.<\/p>
\nToday\u2019s announcement builds on Ayar Labs\u2019 successful close of its $500M Series E funding<\/a>, which included participation from NVIDIA.<\/p> \nAbout Ayar Labs<\/b><\/p> \nAyar Labs is transforming AI infrastructure with the industry\u2019s first proven co-packaged optics (CPO) solution manufactured in partnership with the world\u2019s leading semiconductor ecosystem. By unlocking performance gains and reducing workload costs in power-constrained environments, Ayar Labs\u2019 optical engines are key to enabling next-generation AI scale-up. Founded in 2015, Ayar Labs is funded by domestic and international venture capital firms, as well as strategic investors including AMD, Applied Ventures, MediaTek, NVIDIA, and VentureTech Alliance. For more information, visit www.ayarlabs.com<\/a>.<\/p>