Skip to results
MLSift
← Feed
ML Systems & EfficiencyS2-MoE2608.15018

S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices

Haochen Huang, Shengxuan Qiu, Meng Li

cs.AI

Abstract

Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and Mixture-of-Experts (MoE) have been proposed to improve inference efficiency, naively combining them often incurs excessive verification overhead and poor expert reuse, limiting their effectiveness in memory-bound edge settings. In this work, we propose S2-MoE, an efficient self-speculative decoding framework for MoE inference on edge devices. S2-MoE reduces redundant verification through routing-aware adaptive speculative expansion, improves verification efficiency with reuse-aware expert gating, and aligns draft and target execution via shared context. Implemented in llama$.$cpp, S2-MoE achieves up to $5.3\times$ speedup (about $2.0\times$ on average) over standard autoregressive decoding across diverse MoE models and datasets on edge devices. Code is available at https://github.com/angerybob/S2-MoE.

Topics

Classified with taxonomy v2 on Sat, 5 Sept 2026.

The PDF is 1–3 MB. Open it in your browser's viewer, or load it here.

Open PDF