← all papers · overview

Universal Model Routing For Efficient LLM Inference

Abstract

Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test ti

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).