High-performance RLHF/GRPO pipeline scaling Gemma 3 on GKE Ray Clusters (B200/H200) using NVIDIA NeMo-RL. Includes native FSDP checkpoint merging and zero-shot vLLM benchmarking.
-
Updated
Mar 11, 2026 - Shell
#
nemo-rl
Here is 1 public repository matching this topic...
Improve this page
Add a description, image, and links to the nemo-rl topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nemo-rl topic, visit your repo's landing page and select "manage topics."