#2020th of 31 in Training and fine-tuning
slime
RL post-training framework connecting Megatron training with SGLang rollout
- Stars
- 8.7k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
5,004 on 1 Apr 20268,709 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
slime is a reinforcement-learning post-training framework for LLMs. It runs Megatron for training and SGLang for rollout generation, coordinated by Ray and a shared Data Buffer. Custom generate functions, reward functions, verifiers and environments plug in through documented interfaces. The README says it is the RL framework behind the GLM-4.5 through GLM-5.3 releases.
Who it is for: ML engineers running large-scale RL post-training of LLMs on GPU clusters
Strengths
- Used for RL training of GLM-4.5 through GLM-5.3, per the README
- Megatron args pass through directly; SGLang args use the --sglang- prefix
- Custom generate and reward hooks cover multi-turn, tool-use and agentic rollouts
- Supports fully async rollout, PD disaggregation, delta weight sync, external rollout engines
Weaknesses
- Requires Megatron, SGLang and Ray together; setup is involved
- No Dockerfile or compose file detected in the repository
- Hardware, RAM and VRAM requirements are not stated in the README
- Aimed at multi-GPU RL runs, not small single-machine fine-tuning
What it needs
- GPU required
- Docker
- Needs Megatron-LM, SGLang, Ray
- Models: GLM, Qwen3.8, Qwen3.6, Qwen3.5, Qwen3-Next
Also in Training and fine-tuning
See all 31| Rank | Project | Score |
|---|---|---|
| 1 | unslothDesktop and web app to run, fine-tune and export open models | 88 out of 100 |
| 2 | deepspeedPyTorch library for distributed training of large models with ZeRO | 84 out of 100 |
| 3 | verlReinforcement learning training library for LLM post-training with PPO and GRPO | 84 out of 100 |
| #4 | peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models | 84 out of 100 |
| #5 | trlPost-training library with SFT, DPO, GRPO and KTO trainers | 81 out of 100 |