Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An LLM post-training framework with vLLM for RL Scaling
| Date | Stars |
|---|---|
| 2026-07-31 | 396 |
| 2026-08-02 | 400 |
| 2026-08-06 | 400 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Vime [中文版](./README_zh.md) · [Repository](https://github.com/vllm-project/vime) [](https://docs.vllm.ai/projects/vime/en/latest/) [](https://deepwiki.com/vllm-project/vime) **Vime** is an LLM post-training framework for RL scaling, built on [slime](https://github.com/THUDM/slime). It keeps slime's training stack and data-generation design while using [**vLLM**](https://github.com/vllm-project/vllm) (with [vllm-router](https://github.com/vllm-project/router)) as the default rollout backend. Vime provides two core capabilities: 1. **High-performance training**: Efficient training in various modes by connecting Megatron with vLLM; 2. **Flexible data generation**: Arbitrary training data generation workflows through custom data generation interfaces and server-based engines. Vime inherits broad model support from slime, including: - Qwen series (Qwen3.6, Qwen3.5, Qwen3Next, Qwen3MoE, Qwen3, Qwen2.5); - DeepSeek V3 series (DeepSeek V3, V3.1, DeepSeek R1); - Llama 3. Discussion channels: - [slack](https://vllm-dev.slack.com/archives/C0B8W5QFL22/p1780899164831779) - [wechat group](./imgs/wechat_group.png) ## Positioning The vLLM community horizontally supports many LLM post-training frameworks, including (in alphabetical order) [NeMo RL](https://github.com/NVIDIA-NeMo/RL), [OpenRLHF](https://github.com/openrlhf/openrlhf), [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl), [SkyRL](https://github.com/NovaSky-AI/SkyRL), [verl](https://github.com/verl-project/verl), and so on. We built the Vime project to seamlessly bring slime's proven training paradigm into the vLLM ecosystem, offering a production-ready bridge that aligns both projects' rapid release cycles. We hope that users with different needs can find the right vLLM-ecosystem choice for their workflows. The vLLM community will continue to support the vLLM integration in these post-training frameworks. ## Table of Contents - [Vime](#vime) - [Positioning](#positioning) - [Table of Contents](#table-of-contents) - [Architecture Overview](#architecture-overview) - [Quick Start](#quick-start) - [Arguments Walkthrough](#arguments-walkthrough) - [Developer Guide](#developer-guide) - [slime doc](#slime-doc) - [FAQ](#faq) - [Acknowledgements](#acknowledgements) - [Citation](#citation) ## Architecture Overview  **Module Descriptions**: - **training (Megatron)**: Responsible for the main training process, reads data from the Data Buffer, and synchronizes parameters to the rollout module after training. - **rollout (vLLM + router)**: Launches vLLM inference engines and routes generation requests; produces new data (including rewards/verifier outputs) and stores it in the Data Buffer. - **data buffer**: A bridge module that manages prompt initialization, custom data, and rollout generation methods. ## Quick Start For a comprehensive quick start guide covering environment setup, data preparation, training startup, and key code analysis, please refer to: - [Quick Start Guide](./docs/en/get_started/quick_start.md) We also provide examples for some use cases not covered in the quick start guide; please check [examples](examples/). ## Arguments Walkthrough Arguments in Vime are divided into three categories: 1. **Megatron arguments**: Vime reads all arguments in Megatron. You can configure Megatron by passing arguments like `--tensor-model-parallel-size 2`. 2. **vLLM arguments**: vLLM server and engine options are exposed with a `--vllm-` prefix (for example, `--vllm-gpu-memory-utilization`). Router options live under two prefixes: vllm-router's native options are passed with `--router-` (for example, `--router-policy round_robin`, `--router-request-timeout-secs`), while Vime-side orchestration knobs that tell Vime *where* the router lives use `--vllm-router-` (`--vllm-router-ip`, `--vllm-rout
Excerpt of 6,490 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:47200be7e677bbec, desc:training framework