Marvell Technology, Inc., a leader in data infrastructure semiconductor solutions, today announced it will showcase its comprehensive portfolio of AI data center connectivity and memory solutions at AI Infra Summit 2026—September 15 to 17 at the Santa Clara Convention Center in Santa Clara, California. As AI workloads continue to scale, the ability to move data efficiently between compute, memory and storage has become as important as compute itself. Connectivity now sits at the center of AI infrastructure performance, shaping bandwidth, latency, power consumption, and ultimately the economics of deploying AI at scale.
Marvell to showcase end-to-end AI data center connectivity portfolio at AI Infra Summit 2026
Portfolio designed for scale-up, scale-out, and scale-across applications
Marvell Photonic Fabric enables memory sharing across multiple racks
Teralynx T100 102 Tbps Ethernet switch for large-scale AI networks
CXL memory solutions expand capacity and bandwidth within and across racks
Executive keynote "AI Inference at Scale" by Dave Lazovsky
Marvell offers the industry's most comprehensive connectivity portfolio, designed to enable AI infrastructure to scale efficiently across every distance, driving higher utilization, greater token efficiency, and stronger returns on AI infrastructure investment. This includes next-generation switching technology built to support AI clusters as they scale and advanced telemetry capabilities that speed up infrastructure deployment and reduce mean time to repair after outages or failures. In addition, Marvell's leading-edge optical interconnect and CXL-based memory solutions expand memory capacity and bandwidth both within and across racks.
At AI Infra Summit 2026 (Booth #704), Marvell will highlight the latest advances in its end-to-end data center connectivity portfolio for scale-up, scale-out and scale-across applications, including:
Marvell Photonic Fabric Technology: Enables memory sharing across multiple racks, extending scale beyond traditional distance constraints.
Marvell RELIANT Interconnect Telemetry Platform: Provides real-time visibility into the health and performance of AI data center infrastructure connectivity across optical and electrical links.
Next-generation Switches: The Marvell Teralynx T100 102 Tbps Ethernet switch device delivers increased bandwidth and efficiency for large-scale AI networks.
PCIe-based Scale-up Switching: A 256-lane PCIe 6.0 switch designed to connect more accelerators and devices within scale-up AI systems, along with Marvell-powered electrical, optical and PCIe connectivity for linking AI infrastructure across different distances.
CXL Memory Solutions: CXL-based memory expansion, compression, pooling and near-memory acceleration support memory-intensive AI and cloud workloads, reduce movement of AI datasets between XPUs and accelerate large-scale vector databases used by AI applications.
High-speed Storage Solutions: DPUs and Ethernet switching deliver high-performance access to NVMe storage across the network, and the PCIe 6.0 NVMe SSD controller is optimized for next-generation enterprise and AI storage.
At the AI Infra Summit, Marvell executives will participate in presentations and panels on connectivity and networking topics for next-generation AI data center infrastructure, including a keynote titled "AI Inference at Scale" by Executive Vice President and General Manager of the Data Center Networking Business Group Dave Lazovsky.
About Marvell
To deliver the data infrastructure technology that connects the world, we're building solutions on the most powerful foundation: our partnerships with our customers. Trusted by the world's leading technology companies for over 30 years, we move, store, process and secure the world's data with semiconductor solutions designed for our customers' current needs and future ambitions. Through a process of deep collaboration and transparency, we're ultimately changing the way tomorrow's enterprise, cloud and carrier architectures transform—for the better.
