Tutorials
Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput
Learn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Am
Learn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Amazon S3 and increased aggregate reinforcement learning rollout throughput by 40% for large-scale RLHF and GRPO training.
Related
- Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPod
- Reinforcement fine-tuning on Amazon Bedrock: Best practices
- Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge
Source: AWS ML Blog | 2026-09-25