tommy-yw/runbookhermes/slime
Claude Code and agent skill by tommy-yw/runbookhermes
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install tommy-yw/runbookhermes/slimeSKILL.md
The same SKILL.md was published earlier as tommy-yw/runbookhermes/slime.
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.
When to Use Async
- Large models with long generation times
- High GPU idle time in synchronous mode
- Sufficient memory for buffering
Launch Async Training
Async-Specific Parameters
Workflow 3: Multi-Turn Agentic Training
Use this workflow for training agents with tool use or multi-step reasoning.
Prerequisites
- [ ] Custom generate function for multi-turn logic
- [ ] Tool/environment interface
Step 1: Define Custom Generate Function
Step 2: Launch with Custom Function
See examples/search-r1/ for a complete multi-turn search example.
Configuration Reference
Three Argument Categories
slime uses three types of arguments:
1. Megatron Arguments (passed directly):
2. SGLang Arguments (prefixed with --sglang-):
3. slime Arguments:
Key Constraints
Example: 32 × 8 = 256 × 1
Data Buffer System
slime's data buffer enables flexible data management:
Basic Data Source
Buffered Data Source (Off-Policy)
Common Issues and Solutions
Issue: SGLang Engine Crash
Symptoms: Inference engine dies mid-training
Solutions:
Issue: Weight Sync Timeout
Symptoms: Training hangs after rollout
Solutions:
Issue: OOM During Training
Symptoms: CUDA OOM in backward pass
Solutions:
Issue: Slow Data Loading
Symptoms: GPU idle during data fetch
Solutions:
Supported Models
| Model Family | Configurations | |
|---|---|---|
| GLM | GLM-4.5, GLM-4.6, GLM-4.7, GLM-Z1-9B | |
| Qwen | Qwen3 (4B, 8B, 30B-A3B), Qwen3-MoE, Qwen2.5 | |
| DeepSeek | V3, V3.1, R1 | |
| Llama | Llama 3 (8B, 70B) | |
| Others | Kimi K2, Moonlight-16B |
Each model has pre-configured scripts in scripts/models/.
Advanced Topics
Co-location Mode
Share GPUs between training and inference to reduce memory:
Custom Reward Model
Evaluation Multi-Task
Resources
- Documentation: https://thudm.github.io/slime/
- GitHub: https://github.com/THUDM/slime
- Blog: https://lmsys.org/blog/2025-07-09-slime/
- Examples: See
examples/directory for 14+ worked examples
Security
- Security scanPassed, 96 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingoptional-skills/mlops/slime/SKILL.md
Popularity
- Repository stars
- 513
- Repository forks
- 37
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tommy-yw/runbookhermes/slime)