DriveNets Extends AI Networking Portfolio with High-Capacity AI Fabric Platforms
Powered by Broadcom’s Tomahawk 6 ASIC, the new 1.6 Tbps platforms maximize the performance of very large AI clusters with hundreds of thousands of XPUs RA’ANANA, Israel, July 1, 2026 — DriveNets, a leader in large-scale networking, today announced the expansion of its AI Fabric portfolio, introducing DriveNets 2600SL and 2601S, networking platforms designed for […] The post DriveNets Extends AI Networking Portfolio with High-Capacity AI Fabric Platforms appeared first on HPCwire .
The rapid expansion of large AI models and their increasing computational demands are pushing the limits of current networking infrastructure, making high-capacity AI fabric solutions critical for sustained AI development.
This development addresses a critical bottleneck in scaling AI compute, enabling more efficient and powerful AI clusters which are foundational for continued innovation across various sectors.
The introduction of 1.6 Tbps networking platforms significantly increases the data throughput and efficiency within AI clusters, allowing for the deployment of larger and more complex AI models.
- · Large AI model developers
- · Hyperscale data centers
- · Broadcom
- · DriveNets
- · Companies with less performant networking solutions
- · AI projects constrained by network bandwidth
Improved network performance directly supports the scaling of AI training and inference capabilities.
Faster and larger AI clusters accelerate advancements in various AI applications, making them more practical and accessible.
The widespread adoption of high-capacity AI fabrics could further centralize AI development among organizations with the resources to implement such infrastructure.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at HPCwire