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).
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