Research Training And DistillationResearch Item

Asynchronous RL increases token throughput in Olmo 3

April 6, 2026finbarr

finbarr says moving Olmo 3 from synchronous to asynchronous RL made training code 4x faster in throughput, emphasizing systems-level changes as a lever for scaling.

For Olmo 3, we moved from a synchronous RL setup to an asynchronous one.
This made our code 4x faster in terms of throughput (tokens/second).
finbarr
rltoken throughputtokenstoken throughput

See what authorities are saying right now

This finding is one of many signals tracked across Artificial Intelligence. The live feed updates every few hours with new authority voices, debates, and emerging ideas.

← Back to Artificial Intelligence