Agent skill · research science · nousresearch
slime
RL post-training for LLMs with Megatron and SGLang.
Why this skill is useful
Adds executable scripts for training LLMs using Megatron and SGLang that are not available in public documentation.
What it needs
Requires docker, ray, sglang-router, torch, transformers installed locally. About 5k tokens when loaded. Last updated 2026-08-07. 226,679 stars on the source repository.
What this skill does
slime: LLM Post-Training Framework for RL Scaling slime is an LLM post-training framework from Tsinghua's THUDM team, powering GLM-4.5, GLM-4.6, and GLM-4.7. It connects Megatron-LM for training with SGLang for high-throughput rollout generation. When to Use slime Choose slime when you need: Megatron-LM native training with SGLang inference Custom data generation workflows with flexible data buffers Training GLM, Qwen3, DeepSeek V3, or Llama 3 models Research-grade framework with production backing (Z.ai) Consider alternatives when: You need enterprise-grade stability features → use miles You want flexible backend swapping → use verl You need PyTorch-native abstractions → use torchforge Key Features Training: Megatron-LM with full parallelism support (TP, PP, DP, SP) Rollout: SGLang-based high-throughput generation with router Data Buffer: Flexible prompt management and sample storage Models: GLM-4.x, Qwen3, DeepSeek V3/R1, Llama 3 Architecture Overview Installation From Source Quick Start: GRPO Training --- Workflow 1: Standard GRPO Training Use this workflow for training reasoning models with group-relative advantages. Prerequisites Checklist [ ] Docker environment or Megatron-LM + SGLang installed [ ] Model checkpoint (HuggingFace or Megatron format) [ ] Training data in JSONL format Step 1: Prepare Data Or with chat format: Step 2: Configure Model Choose a pre-configured model script: Step 3: Launch Training Step 4: Monitor Training [ ] Check TensorBoard: tensorboard --logdir outputs/ [ ] Verify reward curves are increasing [ ] Monitor GPU utilization across nodes --- Workflow 2: Asynchronous Training Use async mode for higher throughput by overlapping rollout and training. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nousresearch/slime