<p>➀ Overview of verl framework and its benefits for large-scale reinforcement learning from human feedback (RLHF);</p><p>➁ Introduction to AMD ROCm software support and Docker image for verl v0.3.0.post0;</p><p>➂ Detailed instructions on building Docker images and training scripts for single-node and multi-node setups;</p><p>➃ Performance results of verl on AMD Instinct™ MI300X GPUs, focusing on throughput and convergence accuracy.</p>