verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

By orchestra-research · 772 installs

npx skills add orchestra-research/ai-research-skills --skill verl-rl-training

Source repository · Upstream listing