This is what production RL infra looks like. ICYMI: RL training at scale separates into two distinct problems. - Tight collective comms for …

This is what production RL infra looks like. ICYMI: RL training at scale separates into two distinct problems. - Tight collective comms for the trainer. - Distributed async inference for rollout. Kudos to the @cognition team on this. Their trainer is the secret sauce behind SWE-1.7 and reliable RL rollouts across four datacenters on three continents is easier said than done! We're excited to continue partnering with AI leaders on their path to specialized intelligence. Our RL training spans four datacenters across three continents, combining our own GPUs across multiple clusters with additional compute from inference providers like @FireworksAI_HQ. Only the trainer needs tight collective communication. Rollout inference was distributed, with en…

Source: Fireworks AI (X) | 2026-07-08