MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs
Multimodal large language models (MLLMs) incur substantial inference costs when processing long visual-textual sequences. While existing operation compression methods exploit modality-level redundancy, they largely treat computation within attention heads and shared feed-forward network (FFN) channels as unified units,...
Xu-Dong Wang, Hao Wu, Hao-Zhe Hu et al.
· 0 citations