Agent skill · research science · davila7
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.
Why this skill is useful
Adds executable scripts and workflows for training GLM models with Megatron-LM and SGLang, which are not widely available in public resources.
What it needs
Requires docker, ray, sglang-router, torch, transformers installed locally. About 5k tokens when loaded. Last updated 2026-08-06. 30,138 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 davila7/post-training-slime