Tutorials
Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPod
Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the
Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the container image, launching a Ray cluster from SageMaker Studio, submitting and monitoring the job, and hosting the trained LoRA adapter for inference.
Related
- How to build effective reward functions with AWS Lambda for Amazon Nova model customization
- Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput
- Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge
- Best practices to run inference on Amazon SageMaker HyperPod
Source: AWS ML Blog | 2026-09-25