slime-rl-training
Category: ml-training · License: MIT · Version: 1.0.0
Tags: Reinforcement Learning, Megatron-LM, SGLang, GRPO, Post-Training, GLM
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.Example requests
Ask your agent in plain language, for example:- “How do I launch a GRPO run with slime on GLM-4.7?”
- “I’m running THUDM/slime in Docker on 2 nodes of 8xH100 to RL-train Qwen3-30B-A3B on my train.jsonl, which has prompt and label fields. Training hangs right after the first rollout finishes, and then I get a weight sync timeout. What should I check?”
- “I want to train a search agent with RL. It should call a retrieval tool over several turns, get a reward from the final answer, and run on a Megatron-LM stack with SGLang serving the rollouts. The pipeline should overlap generation and training to avoid idle GPUs. How should I set this up?”
Install
/plugin marketplace add KalarisLabs/research-agent-skills and install the whole ml-training category with /plugin install ml-training@research-agent-skills.
Related
miles-rl-trainingnnsight-remote-interpretabilityverl-rl-training- Skills for machine learning research