MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference

Extrait de la source

Cette page structure un contenu IA & recherche pour faciliter la lecture, la citation et la vérification par les chercheurs, étudiants et moteurs IA.

arXiv:2605.05225v1 Announce Type: new 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-count-based load balancing methods fail to address two unique challenges: (1) Information Heterogeneity, where numerous redundant visual tokens are treated equally to semantically critical ones, and (2) Modality Dynamics, where varying visual to text ratios across tasks lead to resource misallocation. To address these challenges, we propose MACS (Modality-Aware Capacity Scaling), a training-free inference framework. Specifically, MACS introduces an Entropy-Weighted Load mechanism to quantify the semantic value of visual tokens, addressing information heterogeneity. Additionally, the Dynamic Modality-Adaptive Capacity mechanism allocates expert resources based on the real-time modal composition of the input. Extensive experiments demonstrate that MACS significantly outperforms existing methods on various multimodal benchmarks, providing a novel and robust solution for the efficient deployment of MoE MLLMs in EP inference.

Voir la source originale

Source officielle ou originale : arXiv Machine Learning. Vérifiez toujours les détails sur la source primaire.

Retour IA & Recherche