SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding
arXiv:2604.10152v1 Announce Type: cross
Abstract: The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating parameters. However, i…