works on
expert activation cost 1inference efficiency 1large language models 1mixture-of-experts 1speculative decoding 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts

Jincheng Xie, Runheng Liu, Heyan Huang +4

The paper introduces EcoSpec, a cost-aware speculative decoding method that selects draft tokens to minimize expert activation overhead in large mixture-of-experts language models,…