RL rollouts

RL rollouts are sampling for teams that already have a trainer. You keep the algorithm. Grid serves the completions.

This is not managed RFT. Managed reinforcement fine-tuning runs the whole loop: data, reward, train, promote. Rollouts are the inference layer only.

When to use it#

Use rollouts when the trainer is yours and the bottleneck is high-throughput, sticky, multi-turn sampling.

Use managed RFT when you do not want to own a trainer.

What Grid provides#

• OpenAI-compatible chat and completions for rollout traffic.
• Session stickiness so turns of one trajectory can reuse prefix cache on the same replica.
• Capacity that can sit next to production inference, quoted as a reservation.

Weight-update mechanics, regions, and concurrency are sized in the engagement. We do not publish swap times or compression ratios we have not measured on our fleet.

Availability#

Reserved capacity. Talk to us from RL rollouts. There is no anonymous Serverless path for this product.