Skip to main content

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
Category: ml-training · License: MIT · Version: 1.0.0

Install

When to use it

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Full playbook

Read SKILL.md for the complete workflow, references and any scripts. The agent installer copies the full skill folder.