State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We propose that to unlock the potential of SSMs for scaling, they should be combined with MoE. We showcase this on Mamba, a recent SSM-based model that achieves remarkable performance. Our model, MoE-Mamba, outperforms both Mamba and baseline Transformer-MoE. In particular, MoE-Mamba reaches the same performance as Mamba in 2.35× fewer training steps while preserving the inference performance gains of Mamba against Transformer.
@article{arxiv.2401.04081,
title = {MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts},
author = {Maciej Pióro and Kamil Ciebiera and Krystian Król and Jan Ludziejewski and Michał Krutul and Jakub Krajewski and Szymon Antoniak and Piotr Miłoś and Marek Cygan and Sebastian Jaszczur},
journal= {arXiv preprint arXiv:2401.04081},
year = {2024}
}