slime-rl-training - LLM RL post-training using Megatron-LM and SGLang.
Reinforcement Learning Megatron-LM SGLang GRPO
★ 0 · Updated 2026-09-24
Provides guidance and workflows for LLM post-training with RL using the slime framework integrating Megatron-LM and SGLang.
⚙ Execute standard GRPO training ⚙ Run asynchronous RL training ⚙ Conduct multi-turn agentic training