Hugging Face TRL Gets Major Speedup: AsyncGRPO Training Steps Up to 3.5x Faster

ben_burtenshaw · x · 2026-09-23

A major optimization for AsyncGRPO in Hugging Face's TRL is making training steps up to 3.5x faster. The insight: in GRPO the same prompt is sampled G times, and multi-turn rollouts share most of their conversation history, with only the suffix changing as tool results arrive. By leveraging message-level tokenization to share long prefixes across rollouts and using sample packing that balances attention cost across DP ranks, redundant computation in the rollout phase is drastically reduced.

Original post →

More from Infra

Infra channel →