conftrace_

routing

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

confidence tokens (1) error-based feedback (1) cascading (1) flowlets (1) performance-aware (1) switch-local p4 programs (1) framework (1) estimators (1) loras (1) adapter (1)

Papers

A Unified Approach to Routing and Cascading for LLMs ICML 2025 Learning to Route LLMs with Confidence Tokens ICML 2025 Towards Modular LLMs by Building and Reusing a Library of LoRAs ICML 2024 Contra: A Programmable System for Performance-aware Routing NSDI 2020