EasySteer：高性能与可扩展性LLM导向的统一框架

摘要

大语言模型（LLM）引导已成为一种有前景的范式，通过在推理时对隐藏状态进行定向操控来控制模型行为，为昂贵的重新训练提供了一种轻量级替代方案。然而，现有引导框架存在关键局限：计算效率低下、扩展性有限以及功能受限，阻碍了研究进展和实际部署。我们提出了EasySteer，一个基于vLLM构建的高性能、可扩展LLM引导统一框架。该系统采用模块化架构，提供可插拔接口支持基于分析和学习的方法，实现细粒度参数控制，预计算了八个应用领域的引导向量，并配备交互式演示系统。通过与vLLM优化推理引擎的深度集成，EasySteer相比现有框架实现了5.5至11.4倍的加速。大量实验验证了其在缓解过度思考、减少幻觉等关键应用中的有效性。EasySteer将引导从研究技术转变为生产就绪的能力，为可部署、可控的语言模型建立了关键基础设施。

English

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However, existing steering frameworks suffer from critical limitations: computational inefficiency, limited extensibility, and restricted functionality that hinder both research progress and practical deployment. We present EasySteer, a unified framework for high-performance, extensible LLM steering built on vLLM. Our system features modular architecture with pluggable interfaces for both analysis-based and learning-based methods, fine-grained parameter control, pre-computed steering vectors for eight application domains, and an interactive demonstration system. Through deep integration with vLLM's optimized inference engine, EasySteer achieves 5.5-11.4times speedup over existing frameworks. Extensive experiments demonstrate its effectiveness in overthinking mitigation, hallucination reduction, and other key applications. EasySteer transforms steering from research technique to production-ready capability, establishing critical infrastructure for deployable, controllable language models.

EasySteer：高性能与可扩展性LLM导向的统一框架

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering

摘要

Support