Marvell Technology, Inc., a leader in data infrastructure semiconductor solutions, announced a strategic partnership with NVIDIA to bring NVIDIA’s NVLink Fusion technology to customers leveraging Marvell’s custom cloud platform silicon. NVLink Fusion integrates custom XPU silicon with NVIDIA’s NVLink connectivity, rack-scale hardware, and software, delivering a flexible, scalable solution for next-generation AI infrastructure.
Marvell’s Custom Silicon Meets Cutting-Edge NVIDIA Connectivity
Marvell’s custom platform strategy leverages deep expertise in system and semiconductor design, advanced manufacturing, and a broad portfolio of semiconductor IP—including electrical and optical SerDes, die-to-die interconnects, advanced packaging, silicon photonics, co-packaged copper, custom high-bandwidth memory (HBM), and PCIe Gen 7 compute fabric interfaces. This enables Marvell to build innovative platforms in collaboration with customers that dramatically enhance infrastructure performance and efficiency.
Enabling Hyperscalers to Scale AI Workloads
By combining Marvell’s custom silicon with NVIDIA’s NVLink Fusion, hyperscalers gain accelerated access to custom scale-up solutions that meet the demands of AI model training and agentic AI inference—AI driven by learned knowledge and reasoning. NVLink Fusion’s chiplet technology provides up to 1.8TB/s of bidirectional bandwidth, enabling seamless deployment of proprietary XPUs within NVIDIA’s rack-scale systems and end-to-end networking platforms.
Nick Kucharewski, SVP and GM of Marvell’s Cloud Platform Business Unit, stated:
“Marvell and NVIDIA are working together to advance AI factory integration. 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.”
NVIDIA’s Vision for AI-Driven Data Centers
Shar Narasimhan, Director of Accelerated Computing at NVIDIA, emphasized:
“The computing landscape is being reshaped as AI is no longer an application—it is foundational to modern data centers. 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.”
This collaboration marks a significant step forward in delivering scalable, high-performance AI infrastructure tailored to the evolving needs of hyperscalers and cloud providers.
