slime
slime is an LLM post-training framework for RL Scaling.
Stars: 4029
Slime is an LLM post-training framework for RL scaling that provides high-performance training and flexible data generation capabilities. It connects Megatron with SGLang for efficient training and enables custom data generation workflows through server-based engines. The framework includes modules for training, rollout, and data buffer management, offering a comprehensive solution for RL scaling.
README:
slime is an LLM post-training framework for RL scaling, providing two core capabilities:
- High-Performance Training: Supports efficient training in various modes by connecting Megatron with SGLang;
- Flexible Data Generation: Enables arbitrary training data generation workflows through custom data generation interfaces and server-based engines.
slime is the RL-framework behind GLM-4.7, GLM-4.6, GLM-4.5 and apart from models from Z.ai, we also supports the following models:
- Qwen3 series (Qwen3Next, Qwen3MoE, Qwen3), Qwen2.5 series;
- DeepSeek V3 series (DeepSeek V3, V3.1, DeepSeek R1);
- Llama 3.
- Our vision: slime: An SGLang-Native Post-Training Framework for RL Scaling.
- Our ideas on agentic training: Agent-Oriented Design: An Asynchronous and Decoupled Framework for Agentic RL
- v0.1.0 release note: v0.1.0: Redefining High-Performance RL Training Frameworks
- Architecture Overview
- Quick Start
- Projects Built with slime
- Arguments Walkthrough
- Developer Guide
- FAQ & Acknowledgements
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 (SGLang + router): Generates 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.
For a comprehensive quick start guide covering environment setup, data preparation, training startup, and key code analysis, please refer to:
We also provide examples for some use cases not covered in the quick start guide; please check examples.
slime has powered several novel research projects and production systems. Here are some notable examples:
P1 is a family of open-source physics reasoning models trained entirely through reinforcement learning. P1 leverages slime as the RL post training framework, and introduces a multi-stage RL training algorithm that progressively enhances reasoning ability through adaptive learnability adjustment and stabilization mechanisms. Enpowered by this training paradigm, P1 delivers breakthrough performance in open-source physics reasoning.
RLVE introduces an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). With joint training across 400 verifiable environments, RLVE enables each environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses.
TritonForge leverages slime's SFT & RL capabilities to train LLMs that automatically generate optimized GPU kernels. By using a two-stage training approach—supervised fine-tuning followed by reinforcement learning with multi-turn compilation feedback—TritonForge achieves remarkable results in converting PyTorch operations into high-performance Triton kernels.
APRIL introduces a system-level optimization that seamlessly integrates with slime to accelerate the rollout generation phase in RL training. By intelligently over-provisioning requests and actively managing partial completions, APRIL addresses the long-tail generation bottleneck that typically consumes over 90% of RL training time.
qqr (a.k.a. hilichurl) is a lightweight extension for slime designed to evolve open-ended agents. It implements the ArenaRL algorithm to tackle discriminative collapse through tournament-based relative ranking (e.g., Seeded Single-Elimination, Round-Robin) and seamlessly integrates the Model Context Protocol (MCP). qqr leverages slime's high-throughput training capabilities to enable scalable, distributed evolution of agents in standardized, decoupled tool environments.
These projects showcase slime's versatility—from training code-generation models to optimizing RL training systems—making it a powerful foundation for both research and production deployments.
Arguments in slime are divided into three categories:
-
Megatron arguments: slime reads all arguments in Megatron. You can configure Megatron by passing arguments like
--tensor-model-parallel-size 2. -
SGLang arguments: All arguments for the installed SGLang are supported. These arguments must be prefixed with
--sglang-. For example,--mem-fraction-staticshould be passed as--sglang-mem-fraction-static. - slime-specific arguments: Please refer to: slime/utils/arguments.py
For complete usage instructions, please refer to the Usage Documentation.
-
Contributions are welcome! If you have suggestions for new features, performance tuning, or feedback on user experience, feel free to submit an Issue or PR 😊
-
Use pre-commit to ensure code style consistency for your commits:
apt install pre-commit -y
pre-commit install
# run pre-commit to ensure code style consistency
pre-commit run --all-files --show-diff-on-failure --color=always- For debugging tips, please refer to the Debugging Guide
- For frequently asked questions, please see the Q&A
- Special thanks to the following projects & communities: SGLang, Megatron‑LM, mbridge, OpenRLHF, veRL, Pai-Megatron-Patch and others.
- To quote slime, please use:
@misc{slime_github,
author = {Zilin Zhu and Chengxing Xie and Xin Lv and slime Contributors},
title = {slime: An LLM post-training framework for RL Scaling},
year = {2025},
howpublished = {\url{https://github.com/THUDM/slime}},
note = {GitHub repository. Corresponding author: Xin Lv},
urldate = {2025-06-19}
}For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for slime
Similar Open Source Tools
slime
Slime is an LLM post-training framework for RL scaling that provides high-performance training and flexible data generation capabilities. It connects Megatron with SGLang for efficient training and enables custom data generation workflows through server-based engines. The framework includes modules for training, rollout, and data buffer management, offering a comprehensive solution for RL scaling.
verl
veRL is a flexible and efficient reinforcement learning training framework designed for large language models (LLMs). It allows easy extension of diverse RL algorithms, seamless integration with existing LLM infrastructures, and flexible device mapping. The framework achieves state-of-the-art throughput and efficient actor model resharding with 3D-HybridEngine. It supports popular HuggingFace models and is suitable for users working with PyTorch FSDP, Megatron-LM, and vLLM backends.
Fast-dLLM
Fast-DLLM is a diffusion-based Large Language Model (LLM) inference acceleration framework that supports efficient inference for models like Dream and LLaDA. It offers fast inference support, multiple optimization strategies, code generation, evaluation capabilities, and an interactive chat interface. Key features include Key-Value Cache for Block-Wise Decoding, Confidence-Aware Parallel Decoding, and overall performance improvements. The project structure includes directories for Dream and LLaDA model-related code, with installation and usage instructions provided for using the LLaDA and Dream models.
deepteam
Deepteam is a powerful open-source tool designed for deep learning projects. It provides a user-friendly interface for training, testing, and deploying deep neural networks. With Deepteam, users can easily create and manage complex models, visualize training progress, and optimize hyperparameters. The tool supports various deep learning frameworks and allows seamless integration with popular libraries like TensorFlow and PyTorch. Whether you are a beginner or an experienced deep learning practitioner, Deepteam simplifies the development process and accelerates model deployment.
deepeval
DeepEval is a simple-to-use, open-source LLM evaluation framework specialized for unit testing LLM outputs. It incorporates various metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., and runs locally on your machine for evaluation. It provides a wide range of ready-to-use evaluation metrics, allows for creating custom metrics, integrates with any CI/CD environment, and enables benchmarking LLMs on popular benchmarks. DeepEval is designed for evaluating RAG and fine-tuning applications, helping users optimize hyperparameters, prevent prompt drifting, and transition from OpenAI to hosting their own Llama2 with confidence.
bisheng
Bisheng is a leading open-source **large model application development platform** that empowers and accelerates the development and deployment of large model applications, helping users enter the next generation of application development with the best possible experience.
pdr_ai_v2
pdr_ai_v2 is a Python library for implementing machine learning algorithms and models. It provides a wide range of tools and functionalities for data preprocessing, model training, evaluation, and deployment. The library is designed to be user-friendly and efficient, making it suitable for both beginners and experienced data scientists. With pdr_ai_v2, users can easily build and deploy machine learning models for various applications, such as classification, regression, clustering, and more.
Fast-LLM
Fast-LLM is an open-source library designed for training large language models with exceptional speed, scalability, and flexibility. Built on PyTorch and Triton, it offers optimized kernel efficiency, reduced overheads, and memory usage, making it suitable for training models of all sizes. The library supports distributed training across multiple GPUs and nodes, offers flexibility in model architectures, and is easy to use with pre-built Docker images and simple configuration. Fast-LLM is licensed under Apache 2.0, developed transparently on GitHub, and encourages contributions and collaboration from the community.
edge-ai-libraries
The Edge AI Libraries project is a collection of libraries, microservices, and tools for Edge application development. It includes sample applications showcasing generic AI use cases. Key components include Anomalib, Dataset Management Framework, Deep Learning Streamer, ECAT EnableKit, EtherCAT Masterstack, FLANN, OpenVINO toolkit, Audio Analyzer, ORB Extractor, PCL, PLCopen Servo, Real-time Data Agent, RTmotion, Audio Intelligence, Deep Learning Streamer Pipeline Server, Document Ingestion, Model Registry, Multimodal Embedding Serving, Time Series Analytics, Vector Retriever, Visual-Data Preparation, VLM Inference Serving, Intel Geti, Intel SceneScape, Visual Pipeline and Platform Evaluation Tool, Chat Question and Answer, Document Summarization, PLCopen Benchmark, PLCopen Databus, Video Search and Summarization, Isolation Forest Classifier, Random Forest Microservices. Visit sub-directories for instructions and guides.
deeppowers
Deeppowers is a powerful Python library for deep learning applications. It provides a wide range of tools and utilities to simplify the process of building and training deep neural networks. With Deeppowers, users can easily create complex neural network architectures, perform efficient training and optimization, and deploy models for various tasks. The library is designed to be user-friendly and flexible, making it suitable for both beginners and experienced deep learning practitioners.
spec-workflow-mcp
Spec Workflow MCP is a Model Context Protocol (MCP) server that offers structured spec-driven development workflow tools for AI-assisted software development. It includes a real-time web dashboard and a VSCode extension for monitoring and managing project progress directly in the development environment. The tool supports sequential spec creation, real-time monitoring of specs and tasks, document management, archive system, task progress tracking, approval workflow, bug reporting, template system, and works on Windows, macOS, and Linux.
ml-retreat
ML-Retreat is a comprehensive machine learning library designed to simplify and streamline the process of building and deploying machine learning models. It provides a wide range of tools and utilities for data preprocessing, model training, evaluation, and deployment. With ML-Retreat, users can easily experiment with different algorithms, hyperparameters, and feature engineering techniques to optimize their models. The library is built with a focus on scalability, performance, and ease of use, making it suitable for both beginners and experienced machine learning practitioners.
DB-GPT
DB-GPT is an open source AI native data app development framework with AWEL(Agentic Workflow Expression Language) and agents. It aims to build infrastructure in the field of large models, through the development of multiple technical capabilities such as multi-model management (SMMF), Text2SQL effect optimization, RAG framework and optimization, Multi-Agents framework collaboration, AWEL (agent workflow orchestration), etc. Which makes large model applications with data simpler and more convenient.
AReaL
AReaL (Ant Reasoning RL) is an open-source reinforcement learning system developed at the RL Lab, Ant Research. It is designed for training Large Reasoning Models (LRMs) in a fully open and inclusive manner. AReaL provides reproducible experiments for 1.5B and 7B LRMs, showcasing its scalability and performance across diverse computational budgets. The system follows an iterative training process to enhance model performance, with a focus on mathematical reasoning tasks. AReaL is equipped to adapt to different computational resource settings, enabling users to easily configure and launch training trials. Future plans include support for advanced models, optimizations for distributed training, and exploring research topics to enhance LRMs' reasoning capabilities.
AI_Spectrum
AI_Spectrum is a versatile machine learning library that provides a wide range of tools and algorithms for building and deploying AI models. It offers a user-friendly interface for data preprocessing, model training, and evaluation. With AI_Spectrum, users can easily experiment with different machine learning techniques and optimize their models for various tasks. The library is designed to be flexible and scalable, making it suitable for both beginners and experienced data scientists.
AimRT
AimRT is a basic runtime framework for modern robotics, developed in modern C++ with lightweight and easy deployment. It integrates research and development for robot applications in various deployment scenarios, providing debugging tools and observability support. AimRT offers a plug-in development interface compatible with ROS2, HTTP, Grpc, and other ecosystems for progressive system upgrades.
For similar tasks
LaVague
LaVague is an open-source Large Action Model framework that uses advanced AI techniques to compile natural language instructions into browser automation code. It leverages Selenium or Playwright for browser actions. Users can interact with LaVague through an interactive Gradio interface to automate web interactions. The tool requires an OpenAI API key for default examples and offers a Playwright integration guide. Contributors can help by working on outlined tasks, submitting PRs, and engaging with the community on Discord. The project roadmap is available to track progress, but users should exercise caution when executing LLM-generated code using 'exec'.
DocsGPT
DocsGPT is an open-source documentation assistant powered by GPT models. It simplifies the process of searching for information in project documentation by allowing developers to ask questions and receive accurate answers. With DocsGPT, users can say goodbye to manual searches and quickly find the information they need. The tool aims to revolutionize project documentation experiences and offers features like live previews, Discord community, guides, and contribution opportunities. It consists of a Flask app, Chrome extension, similarity search index creation script, and a frontend built with Vite and React. Users can quickly get started with DocsGPT by following the provided setup instructions and can contribute to its development by following the guidelines in the CONTRIBUTING.md file. The project follows a Code of Conduct to ensure a harassment-free community environment for all participants. DocsGPT is licensed under MIT and is built with LangChain.
Ollamac
Ollamac is a macOS app designed for interacting with Ollama models. It is optimized for macOS, allowing users to easily use any model from the Ollama library. The app features a user-friendly interface, chat archive for saving interactions, and real-time communication using HTTP streaming technology. Ollamac is open-source, enabling users to contribute to its development and enhance its capabilities. It requires macOS 14 or later and the Ollama system to be installed on the user's Mac with at least one Ollama model downloaded.
npi
NPi is an open-source platform providing Tool-use APIs to empower AI agents with the ability to take action in the virtual world. It is currently under active development, and the APIs are subject to change in future releases. NPi offers a command line tool for installation and setup, along with a GitHub app for easy access to repositories. The platform also includes a Python SDK and examples like Calendar Negotiator and Twitter Crawler. Join the NPi community on Discord to contribute to the development and explore the roadmap for future enhancements.
ain
DeFiChain is a blockchain platform dedicated to enabling decentralized finance with Bitcoin-grade security, strength, and immutability. It offers fast, intelligent, and transparent financial services accessible to everyone. DeFiChain has made significant modifications from Bitcoin Core, including moving to Proof-of-Stake, introducing a masternode model, supporting a community fund, anchoring to the Bitcoin blockchain, and enhancing decentralized financial transaction and opcode support. The platform is under active development with regular releases and contributions are welcomed.
doc-comments-ai
doc-comments-ai is a tool designed to automatically generate code documentation using language models. It allows users to easily create documentation comment blocks for methods in various programming languages such as Python, Typescript, Javascript, Java, Rust, and more. The tool supports both OpenAI and local LLMs, ensuring data privacy and security. Users can generate documentation comments for methods in files, inline comments in method bodies, and choose from different models like GPT-3.5-Turbo, GPT-4, and Azure OpenAI. Additionally, the tool provides support for Treesitter integration and offers guidance on selecting the appropriate model for comprehensive documentation needs.
eval-dev-quality
DevQualityEval is an evaluation benchmark and framework designed to compare and improve the quality of code generation of Language Model Models (LLMs). It provides developers with a standardized benchmark to enhance real-world usage in software development and offers users metrics and comparisons to assess the usefulness of LLMs for their tasks. The tool evaluates LLMs' performance in solving software development tasks and measures the quality of their results through a point-based system. Users can run specific tasks, such as test generation, across different programming languages to evaluate LLMs' language understanding and code generation capabilities.
ansible-power-aix
The IBM Power Systems AIX Collection provides modules to manage configurations and deployments of Power AIX systems, enabling workloads on Power platforms as part of an enterprise automation strategy through the Ansible ecosystem. It includes example best practices, requirements for AIX versions, Ansible, and Python, along with resources for documentation and contribution.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.