Speculative MoE: Communication Efficient Parallel MoE Inference with Speculative Token and Expert Pre-scheduling

no code implementations • 6 Mar 2025 • Yan Li, Pengfei Zheng, Shuang Chen, Zewei Xu, Yuanhao Lai, Yunfei Du, Zhengang Wang

MoE (Mixture of Experts) prevails as a neural architecture that can scale modern transformer-based LLMs (Large Language Models) to unprecedented scales.

Mixture-of-Experts Scheduling