EasySteer：一個統一的高性能與可擴展LLM導向框架

摘要

大型語言模型（LLM）導向技術已成為一種前景廣闊的範式，通過對隱藏狀態的定向操控來在推理時控制模型行為，提供了一種輕量級的替代方案，避免了昂貴的重新訓練。然而，現有的導向框架存在關鍵限制：計算效率低下、擴展性有限以及功能受限，這些都阻礙了研究進展和實際部署。我們提出了EasySteer，這是一個基於vLLM構建的高性能、可擴展的LLM導向統一框架。我們的系統具有模塊化架構，提供可插拔的接口，支持基於分析和基於學習的方法，精細的參數控制，預先計算的八個應用領域的導向向量，以及一個互動演示系統。通過與vLLM優化的推理引擎深度集成，EasySteer相比現有框架實現了5.5至11.4倍的加速。大量實驗證明了其在緩解過度思考、減少幻覺以及其他關鍵應用中的有效性。EasySteer將導向技術從研究手段轉變為生產就緒的能力，為可部署、可控的語言模型建立了關鍵基礎設施。

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：一個統一的高性能與可擴展LLM導向框架

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

摘要

Support