# NVIDIA explains how to speed up RL weight refit with the Reshard Collective

> Original title: Accelerating Reinforcement Learning Weight Refit with the Reshard Collective

- Source: NVIDIA Technical Blog
- Published: 2026-11-06T18:03:26.000Z
- Bad Influence: https://badinfluence.news/items/jt3ys7agdhfb084ljqlwym8p8
- Original: https://developer.nvidia.com/blog/accelerating-reinforcement-learning-weight-refit-with-the-reshard-collective/

## Summary

NVIDIA's Technical Blog describes the Reshard Collective, a method for accelerating weight refits in reinforcement learning post-training. The problem it addresses is that disaggregated setups run inference and training on separate GPUs, so the inference side must periodically receive updated policy weights from the training side.