UniExit: A Unified Latency-Aware Early-Exit Runtime for Heterogeneous Edge AI

arXiv:2611.09159 · cs.DC · Submitted 2026-11-06 · Read on arXiv

cs.DC

Submitted: 2026-11-06

Updated: 2026-11-06

Code: https://github.com/meta-llama/llamamodels

Terminology

Sources

Related papers