Menu

#ResHard

1 post

Feed
1 of 1 post
Accelerating Reinforcement Learning Weight Refit with the Reshard Collective
🖼️
0Read More

Accelerating Reinforcement Learning Weight Refit with the Reshard Collective

NVIDIA Technical Blog·Tanya Lenz·9 days ago
#MGFUI4nP
#developer#refit#reshard#gpus#training

During reinforcement learning (RL) post-training, training trajectories are generated on the fly by running inference with the current policy model.

15s