algorithmicsuperintelligence/optillm
OptiLLM is an OpenAI API-compatible inference proxy that significantly boosts LLM accuracy and performance on reasoning tasks using 20+ state-of-the-art optimization techniques, requiring zero training.
Core Features
Quick Start
pip install optillmDetailed Introduction
OptiLLM serves as an intelligent inference proxy designed to dramatically enhance the accuracy and performance of Large Language Models (LLMs) on complex reasoning tasks. By integrating over 20 cutting-edge optimization techniques, from simple best-of-N to advanced MCTS and planning, it allows users to achieve 2-10x better results without any model training or fine-tuning. Its OpenAI API compatibility ensures a seamless drop-in replacement for existing LLM integrations, making advanced reasoning capabilities accessible across various providers and models in production environments.