MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
概要
arXiv:2605.05225v1 Announce Type: cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP) inference due to the straggler effect. This issue is worsened in the multimodal context, as existing token…
