How GPUs and RDUs work together | SambaNova at COMPUTEX 2026

At COMPUTEX, SambaNova demonstrated what the next era of AI inference looks like: Premium inference for AI agents powered by GPUs and RDUs, running live in the newly-announced VC2 data center for the first time. Using Nvidia’s B200 GPU for prefill and SambaNova’s SN40 RDU for decode, the inference speed generated is 2X the speed of B200-only configurations, as verified by Artificial Intelligence. This is running today out of Vector Core Compute's (VC2) data center, with Together.AI as the first commercial customer to use the inference capabilities from VC2.