DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The paper introduces Modality-Aware Expert Pruning (MAEP), a training‑free method that decomposes expert importance by modality in a single forward pass for Mixture‑of‑Experts multimodal large language models. MAEP uses a Delta‑H Output metric to measure the impact of removing an expert and leverages low‑attention vision tokens as a stable pruning signal, while preserving text‑side importance. Experiments on three MoE‑based MLLMs show that MAEP reduces the BF16 expert weight footprint by about 27 GB (≈47% of total memory), enabling a 58 GB model to fit on a single 40 GB GPU and outperforming modality‑agnostic baselines on most multimodal benchmarks.
arXiv:2511. 04805v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input.
MWOP (Modality-aware Width-wise Operation Pruning) is a method that independently prunes visual‑to‑visual, text‑to‑visual, and text‑to‑text attention paths within each layer of multimodal large language models, and separately selects feed‑forward network channels for visual and textual inputs. It uses a first‑order Taylor criterion to guide pruning, re‑evaluates FFN importance after attention pruning, and applies LoRA‑based recovery training. The approach is paired with path‑sparse Triton attention kernels and compact visual‑side FFN execution to achieve practical acceleration, preserving token sequences while reducing computation. "whyItMatters":"MWOP achieves a 1.6× prefill speedup on LLaVA‑OneVision‑7B while retaining 99.7% performance, and further boosts token‑compression methods to 2.9× and 2.7× speedups, demonstrating its effectiveness across architectures."
arXiv:2606. 31903v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation.
arXiv:2605. 25820v2 Announce Type: replace Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel.
arXiv:2609.01200v1 Announce Type: new Abstract: When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddi...