
SpecForge
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Stars: 407

SpecForge is a powerful tool for generating API specifications from code. It helps developers to easily create and maintain accurate API documentation by extracting information directly from the codebase. With SpecForge, users can streamline the process of documenting APIs, ensuring consistency and reducing manual effort. The tool supports various programming languages and frameworks, making it versatile and adaptable to different development environments. By automating the generation of API specifications, SpecForge enhances collaboration between developers and stakeholders, improving overall project efficiency and quality.
README:
SpecForge is an ecosystem project developed by the SGLang team. It is a framework for training speculative decoding models so that you can smoothly port them over to the SGLang serving framework to speed up your inference.
We have seen many open-source projects for speculative decoding, but most of them are not well-maintained or not directly compatible with SGLang. We prepared this project because we wish that the open-source community can enjoy a speculative decoding framework that is
- regularly maintained by the SpecForge team: the code is runnable out-of-the-box
- directly compatible with SGLang: there is no additional efforts for porting to SGLang
- provide performant training capabilities: we provided online/offline/tensor-parallel/FSDP to suit your needs
Check out our documentation to get started.
- [2025-08] 🔔 SpecForge is listed as a flagship project in LMSYS. Congratulations to the SpecForge team!
- [2025-08] 🔥 SpecForge powered the Eagle3 draft model for GPT-OSS. Check out the blog at LMSYS.org
- [2025-07] 🔥 SpecForge is released together with Llama4-Eagle3 checkpoints. Check out our blog at LMSYS.org
We would like to express our sincere gratitude to the official EAGLE team, especially Hongyang Zhang and Yuhui Li, for their invaluable contributions and support. Our thanks also go to the NVIDIA team—particularly Avery H and Izzy Putterman—and to the Google team, especially Ying Wang, for their insightful discussions and generous assistance throughout the project.
We are especially grateful to Meituan for their strong backing and meaningful contributions, which played a vital role in driving this project forward.
This project has also been inspired by many outstanding open-source projects from the LLM community, including EAGLE, BaldEagle, and TensorRT-Model-Optimizer and others. Their contributions and shared knowledge have greatly benefited our work.
We would like to extend our sincere thanks to Voltage Park, our official infrastructure partner. As part of a formal collaboration with the SGLang team, Voltage Park provided critical GPU resources that empowered us to train and evaluate large-scale speculative decoding models efficiently and reliably. This partnership was instrumental in making SpecForge possible. We deeply appreciate Voltage Park’s mission to make cutting-edge AI infrastructure more accessible, and we look forward to continued collaboration as we push the boundaries of open-source LLM serving and optimization.
@misc{specforge2025,
title={SpecForge: Train speculative decoding models effortlessly},
author={Shenggui Li, Yikai Zhu, Chao Wang, Fan Yin, Shuai Shi, Yubo Wang, Yi Zhang, Yingyi Huang, Haoshuai Zheng, Yineng Zhang},
year={2025},
publisher={GitHub},
howpublished={\url{https://github.com/sgl-project/specforge}},
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for SpecForge
Similar Open Source Tools

SpecForge
SpecForge is a powerful tool for generating API specifications from code. It helps developers to easily create and maintain accurate API documentation by extracting information directly from the codebase. With SpecForge, users can streamline the process of documenting APIs, ensuring consistency and reducing manual effort. The tool supports various programming languages and frameworks, making it versatile and adaptable to different development environments. By automating the generation of API specifications, SpecForge enhances collaboration between developers and stakeholders, improving overall project efficiency and quality.

arcade-ai
Arcade AI is a developer-focused tooling and API platform designed to enhance the capabilities of LLM applications and agents. It simplifies the process of connecting agentic applications with user data and services, allowing developers to concentrate on building their applications. The platform offers prebuilt toolkits for interacting with various services, supports multiple authentication providers, and provides access to different language models. Users can also create custom toolkits and evaluate their tools using Arcade AI. Contributions are welcome, and self-hosting is possible with the provided documentation.

aiounifi
Aiounifi is a Python library that provides a simple interface for interacting with the Unifi Controller API. It allows users to easily manage their Unifi network devices, such as access points, switches, and gateways, through automated scripts or applications. With Aiounifi, users can retrieve device information, perform configuration changes, monitor network performance, and more, all through a convenient and efficient API wrapper. This library simplifies the process of integrating Unifi network management into custom solutions, making it ideal for network administrators, developers, and enthusiasts looking to automate and streamline their network operations.

LocalLLMClient
LocalLLMClient is a Swift package designed to interact with local Large Language Models (LLMs) on Apple platforms. It supports GGUF, MLX models, and the FoundationModels framework, providing streaming API, multimodal capabilities, and tool calling functionalities. Users can easily integrate this tool to work with various models for text generation and processing. The package also includes advanced features for low-level API control and multimodal image processing. LocalLLMClient is experimental and subject to API changes, offering support for iOS, macOS, and Linux platforms.

WorkflowAI
WorkflowAI is a powerful tool designed to streamline and automate various tasks within the workflow process. It provides a user-friendly interface for creating custom workflows, automating repetitive tasks, and optimizing efficiency. With WorkflowAI, users can easily design, execute, and monitor workflows, allowing for seamless integration of different tools and systems. The tool offers advanced features such as conditional logic, task dependencies, and error handling to ensure smooth workflow execution. Whether you are managing project tasks, processing data, or coordinating team activities, WorkflowAI simplifies the workflow management process and enhances productivity.

promptl
Promptl is a versatile command-line tool designed to streamline the process of creating and managing prompts for user input in various programming projects. It offers a simple and efficient way to prompt users for information, validate their input, and handle different scenarios based on their responses. With Promptl, developers can easily integrate interactive prompts into their scripts, applications, and automation workflows, enhancing user experience and improving overall usability. The tool provides a range of customization options and features, making it suitable for a wide range of use cases across different programming languages and environments.

airbrussh
Airbrussh is a Capistrano plugin that enhances the output of Capistrano's deploy command. It provides a more detailed and structured view of the deployment process, including color-coded output, timestamps, and improved formatting. Airbrussh aims to make the deployment logs easier to read and understand, helping developers troubleshoot issues and monitor deployments more effectively. It is a useful tool for teams working with Capistrano to streamline their deployment workflows and improve visibility into the deployment process.

vibe
Vibe Design System is a collection of packages for React.js development, providing components, styles, and guidelines to streamline the development process and enhance user experience. It includes a Core component library, Icons library, Testing utilities, Codemods, and more. The system also features an MCP server for intelligent assistance with component APIs, usage examples, icons, and best practices. Vibe 2 is no longer actively maintained, with users encouraged to upgrade to Vibe 3 for the latest improvements and ongoing support.

deepflow
DeepFlow is an open-source project that provides deep observability for complex cloud-native and AI applications. It offers Zero Code data collection with eBPF for metrics, distributed tracing, request logs, and function profiling. DeepFlow is integrated with SmartEncoding to achieve Full Stack correlation and efficient access to all observability data. With DeepFlow, cloud-native and AI applications automatically gain deep observability, removing the burden of developers continually instrumenting code and providing monitoring and diagnostic capabilities covering everything from code to infrastructure for DevOps/SRE teams.

trubrics-sdk
Trubrics-sdk is a software development kit designed to facilitate the integration of analytics features into applications. It provides a set of tools and functionalities that enable developers to easily incorporate analytics capabilities, such as data collection, analysis, and reporting, into their software products. The SDK streamlines the process of implementing analytics solutions, allowing developers to focus on building and enhancing their applications' functionality and user experience. By leveraging trubrics-sdk, developers can quickly and efficiently integrate robust analytics features, gaining valuable insights into user behavior and application performance.

Memento
Memento is a lightweight and user-friendly version control tool designed for small to medium-sized projects. It provides a simple and intuitive interface for managing project versions and collaborating with team members. With Memento, users can easily track changes, revert to previous versions, and merge different branches. The tool is suitable for developers, designers, content creators, and other professionals who need a streamlined version control solution. Memento simplifies the process of managing project history and ensures that team members are always working on the latest version of the project.

obsidian-NotEMD
Obsidian-NotEMD is a plugin for the Obsidian note-taking app that allows users to export notes in various formats without converting them to EMD. It simplifies the process of sharing and collaborating on notes by providing seamless export options. With Obsidian-NotEMD, users can easily export their notes to PDF, HTML, Markdown, and other formats directly from Obsidian, saving time and effort. This plugin enhances the functionality of Obsidian by streamlining the export process and making it more convenient for users to work with their notes across different platforms and applications.

LightLLM
LightLLM is a lightweight library for linear and logistic regression models. It provides a simple and efficient way to train and deploy machine learning models for regression tasks. The library is designed to be easy to use and integrate into existing projects, making it suitable for both beginners and experienced data scientists. With LightLLM, users can quickly build and evaluate regression models using a variety of algorithms and hyperparameters. The library also supports feature engineering and model interpretation, allowing users to gain insights from their data and make informed decisions based on the model predictions.

hujiang_dictionary
Hujiang Dictionary is a tool that provides translation services between Japanese, Chinese, and English. It supports various translation modes such as Japanese to Chinese, Chinese to Japanese, English to Japanese, and more. The tool utilizes cloud services like Telegram, Lambda, and Cloudflare Workers for different deployment options. Users can interact with the tool via a command-line interface (CLI) to perform translations and access online resources like weblio and Google Translate. Additionally, the tool offers a Telegram bot for users to access translation services conveniently. The tool also supports setting up and managing databases for storing translation data.

tools
Strands Agents Tools is a community-driven project that provides a powerful set of tools for your agents to use. It bridges the gap between large language models and practical applications by offering ready-to-use tools for file operations, system execution, API interactions, mathematical operations, and more. The tools cover a wide range of functionalities including file operations, shell integration, memory storage, web infrastructure, HTTP client, Slack client, Python execution, mathematical tools, AWS integration, image and video processing, audio output, environment management, task scheduling, advanced reasoning, swarm intelligence, dynamic MCP client, parallel tool execution, browser automation, diagram creation, RSS feed management, and computer automation.

J.A.R.V.I.S.
J.A.R.V.I.S.1.0 is an advanced virtual assistant tool designed to assist users in various tasks. It provides a wide range of functionalities including voice commands, task automation, information retrieval, and communication management. With its intuitive interface and powerful capabilities, J.A.R.V.I.S.1.0 aims to enhance productivity and streamline daily activities for users.
For similar tasks

aide
Aide is a code-first API documentation and utility library for Rust, along with other related utility crates for web-servers. It provides tools for creating API documentation and handling JSON request validation. The repository contains multiple crates that offer drop-in replacements for existing libraries, ensuring compatibility with Aide. Contributions are welcome, and the code is dual licensed under MIT and Apache-2.0. If Aide does not meet your requirements, you can explore similar libraries like paperclip, utoipa, and okapi.

SpecForge
SpecForge is a powerful tool for generating API specifications from code. It helps developers to easily create and maintain accurate API documentation by extracting information directly from the codebase. With SpecForge, users can streamline the process of documenting APIs, ensuring consistency and reducing manual effort. The tool supports various programming languages and frameworks, making it versatile and adaptable to different development environments. By automating the generation of API specifications, SpecForge enhances collaboration between developers and stakeholders, improving overall project efficiency and quality.

mattermost-plugin-ai
The Mattermost AI Copilot Plugin is an extension that adds functionality for local and third-party LLMs within Mattermost v9.6 and above. It is currently experimental and allows users to interact with AI models seamlessly. The plugin enhances the user experience by providing AI-powered assistance and features for communication and collaboration within the Mattermost platform.

agent-hub
Agent Hub is a platform for AI Agent solutions, containing three different projects aimed at transforming enterprise workflows, enhancing personalized language learning experiences, and enriching multimodal interactions. The projects include GitHub Sentinel for project management and automatic updates, LanguageMentor for personalized language learning support, and ChatPPT for multimodal AI-driven insights and PowerPoint automation in enterprise settings. The future vision of agent-hub is to serve as a launchpad for more AI Agents catering to different industries and pushing the boundaries of AI technology. Users are encouraged to explore, clone the repository, and contribute to the development of transformative AI agents.

Conversation-Knowledge-Mining-Solution-Accelerator
The Conversation Knowledge Mining Solution Accelerator enables customers to leverage intelligence to uncover insights, relationships, and patterns from conversational data. It empowers users to gain valuable knowledge and drive targeted business impact by utilizing Azure AI Foundry, Azure OpenAI, Microsoft Fabric, and Azure Search for topic modeling, key phrase extraction, speech-to-text transcription, and interactive chat experiences.
For similar jobs

google.aip.dev
API Improvement Proposals (AIPs) are design documents that provide high-level, concise documentation for API development at Google. The goal of AIPs is to serve as the source of truth for API-related documentation and to facilitate discussion and consensus among API teams. AIPs are similar to Python's enhancement proposals (PEPs) and are organized into different areas within Google to accommodate historical differences in customs, styles, and guidance.

kong
Kong, or Kong API Gateway, is a cloud-native, platform-agnostic, scalable API Gateway distinguished for its high performance and extensibility via plugins. It also provides advanced AI capabilities with multi-LLM support. By providing functionality for proxying, routing, load balancing, health checking, authentication (and more), Kong serves as the central layer for orchestrating microservices or conventional API traffic with ease. Kong runs natively on Kubernetes thanks to its official Kubernetes Ingress Controller.

speakeasy
Speakeasy is a tool that helps developers create production-quality SDKs, Terraform providers, documentation, and more from OpenAPI specifications. It supports a wide range of languages, including Go, Python, TypeScript, Java, and C#, and provides features such as automatic maintenance, type safety, and fault tolerance. Speakeasy also integrates with popular package managers like npm, PyPI, Maven, and Terraform Registry for easy distribution.

apicat
ApiCat is an API documentation management tool that is fully compatible with the OpenAPI specification. With ApiCat, you can freely and efficiently manage your APIs. It integrates the capabilities of LLM, which not only helps you automatically generate API documentation and data models but also creates corresponding test cases based on the API content. Using ApiCat, you can quickly accomplish anything outside of coding, allowing you to focus your energy on the code itself.

aiohttp-pydantic
Aiohttp pydantic is an aiohttp view to easily parse and validate requests. You define using function annotations what your methods for handling HTTP verbs expect, and Aiohttp pydantic parses the HTTP request for you, validates the data, and injects the parameters you want. It provides features like query string, request body, URL path, and HTTP headers validation, as well as Open API Specification generation.

ain
Ain is a terminal HTTP API client designed for scripting input and processing output via pipes. It allows flexible organization of APIs using files and folders, supports shell-scripts and executables for common tasks, handles url-encoding, and enables sharing the resulting curl, wget, or httpie command-line. Users can put things that change in environment variables or .env-files, and pipe the API output for further processing. Ain targets users who work with many APIs using a simple file format and uses curl, wget, or httpie to make the actual calls.

OllamaKit
OllamaKit is a Swift library designed to simplify interactions with the Ollama API. It handles network communication and data processing, offering an efficient interface for Swift applications to communicate with the Ollama API. The library is optimized for use within Ollamac, a macOS app for interacting with Ollama models.

ollama4j
Ollama4j is a Java library that serves as a wrapper or binding for the Ollama server. It facilitates communication with the Ollama server and provides models for deployment. The tool requires Java 11 or higher and can be installed locally or via Docker. Users can integrate Ollama4j into Maven projects by adding the specified dependency. The tool offers API specifications and supports various development tasks such as building, running unit tests, and integration tests. Releases are automated through GitHub Actions CI workflow. Areas of improvement include adhering to Java naming conventions, updating deprecated code, implementing logging, using lombok, and enhancing request body creation. Contributions to the project are encouraged, whether reporting bugs, suggesting enhancements, or contributing code.