Marvell and NVIDIA to Provide Custom Solutions for Advanced AI Infrastructure

Marvell Technology, Inc. announced it is teaming with NVIDIA Corp. to offer NVIDIA NVLink Fusion technology to customers employing Marvell custom cloud platform silicon.

NVLink Fusion is a new offering from NVIDIA for integrating custom XPU silicon with NVLink connectivity, rack-scale hardware architecture, software and other technology, providing customers with flexibility and choice in developing next-gen AI infrastructure.

The Marvell custom platform strategy seeks to deliver breakthrough results through unique semiconductor designs and innovative approaches. By combining expertise in system and semiconductor design, advanced process manufacturing, and a comprehensive portfolio of semiconductor platform solutions and IP – including electrical and optical serializer/deserializers (SerDes), die-to-die interconnects for 2D and 3D devices, advanced packaging, silicon photonics, co-packaged copper, custom high-bandwidth memory (HBM), SoC fabrics, optical IO, and compute fabric interfaces such as PCIe Gen 7 –  Marvell is able to create platforms in collaboration with customers that transform infrastructure performance, efficiency and value.

The firm’s custom silicon with NVLink Fusion offers hyperscalers an accelerated path to custom scale-up solutions that meet the rigorous demands of model training and agentic AI inference – where outputs are driven by learned knowledge and reasoning. Hyperscalers can now deploy these customized capabilities across their AI data center infrastructure while also leveraging their architecture investments in NVLink.

NVLink gives cloud providers an easy path to scale out AI factories to millions of custom XPUs by effectively enabling them to integrate their proprietary XPUs into NVIDIA’s rack-scale systems and the NVIDIA end-to-end networking platform. The core technology of NVLink Fusion is a chiplet delivering up to 1.8TB/s of bidirectional bandwidth.

“Marvell and NVIDIA are working together to advance AI factory integration,” said Nick Kucharewski, SVP and GM, cloud platform business unit, Marvell. “Through this collaboration, we offer customers the flexibility to rapidly deploy scalable AI infrastructure with the bandwidth, performance and reliability required to support advanced AI models.“

“The computing landscape is being reshaped as AI is no longer an application – it is foundational to modern data centers,” said Shar Narasimhan, director, accelerated computing, NVIDIA. “NVLink Fusion extends NVIDIA’s open platform to partners like Marvell, enabling hyperscalers to scale out AI factories to millions of GPUs, using custom silicon, NVIDIA’s rack-scale systems and the NVIDIA end-to-end networking platform, to meet the world’s accelerating demand for intelligence.”