News: Optoelectronics
23 March 2026
Ayar Labs and Wiwynn partner on CPO for rack-scale AI systems
Silicon photonics-based chip-to-chip optical connectivity firm Ayar Labs of San Jose, CA, USA — which is pioneering co-packaged optics (CPO) for AI scale-up — and Wiwynn Corp of Taipei, Taiwan, a cloud IT infrastructure provider for data centers, have announced a strategic partnership to deliver optically connected, rack-scale AI systems that support next-generation hyperscale AI workloads.
As AI models drive compute demand, traditional copper interconnects increasingly constrain performance, system growth, and power efficiency. By combining Ayar Labs’ CPO solution with Wiwynn’s rack-level system design and manufacturing capabilities, the two companies say they are enabling a new class of rack-scale AI infrastructure that’s not constrained by the bandwidth and reach limitations of copper.
“AI infrastructure is outgrowing the limits of copper, and hyperscalers need a fundamentally new approach to scale,” says Ayar Labs’ CEO & co-founder Mark Wade. “Optically connected racks eliminate the interconnect bottleneck and unlock the next order of magnitude in performance and efficiency. By combining Wiwynn’s global system and manufacturing leadership with Ayar Labs’ co-packaged optics expertise, we are delivering pioneering, rack-scale architectures purpose-built for optically connected scale-up AI networks.”
The joint solution integrates Ayar Labs’ AI scale-up CPO technology, including TeraPHY optical engines powered by the SuperNova remote light source, into Wiwynn’s rack-level architecture for next-generation data centers. Together, the companies say they are solving the practical deployment challenges that hyperscalers face, including optical fiber management, integration of CPO-enabled AI ASICs, thermal management, power efficiency, and manufacturability.
“Silicon photonics is reshaping how AI infrastructure is built,” says Wiwynn’s president & CEO William Lin. “With Ayar Labs’ leadership in co‑packaged optics and Wiwynn’s strengths in rack‑level integration and manufacturing, we accelerate the shift from silicon‑ready innovation to system‑ready solutions,” he adds. “Together, we are enabling advanced optical I/O that delivers greater scalability and energy efficiency for cloud and hyperscale customers, powering next‑generation AI data centers.”
The new optically connected rack-scale AI infrastructure is designed to scale to 1024 AI accelerators and beyond, with each accelerator capable of delivering more than 100Tbps of optical connectivity, enabling thousands of accelerators to operate as a single, unified system across multiple racks. The solution incorporates a liquid-cooled architecture optimized for high-power operation, including support for external laser small-form-factor pluggable (ELSFP) light sources, advanced fiber management, and serviceable system designs required for hyperscale environments.
Wiwynn has over a decade of experience delivering rack-level IT solutions to cloud service providers, with end-to-end capabilities spanning board design, system integration, and high-volume L10 and L11 rack delivery. It has shipped general and AI servers to more than 750 data centers worldwide, supported by manufacturing operations in Taiwan, the USA, Mexico, Malaysia, and the Czech Republic.
At the Optical Fiber Communication Conference (OFC 2026) in Los Angeles (15–19 March), Ayar Labs and Wiwynn showcased their joint AI CPO solution, highlighting an HVDC (high-voltage direct current)-enabled, rack-level system architecture for next-generation AI data centers. It features a 100% liquid-cooled AI system reference design with support of ELSFP SuperNova remote light sources and AI ASICs with optical engines.
Ayar Labs names Sankara Venkateswaran as VP of engineering
Ayar Labs and Alchip to scale AI infrastructure with co-packaged optics
