Same prompt. Same model. Two stacks.

At #Computex, we demonstrated disaggregated inference live: GPUs handling prefill, SambaNova RDUs handling decode, and CPUs orchestrating agent execution.

The result? Up to 2X the speed of B200-only configurations 🦾 pic.twitter.com/YYP8o6WYrK

— SambaNova (@SambaNovaAI) 9 juin 2026

Same prompt. Same model. Two stacks. At #Computex, we demonstrated disaggregated inference live: GPUs handling prefill, SambaNova RDUs handling decode, and CPUs orchestrating agent execution. The result? Up to 2X the speed of B200-only configurations

→ View original post on X — @sambanovaai