REVIEW 5 cited by
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
read the original abstract
The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://aka.ms/MMInference.
Forward citations
Cited by 5 Pith papers
-
AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
AdaSpark delivers up to 57% FLOP reduction in Video-LLMs for long videos through adaptive cube- and token-level sparsity without apparent loss in performance on hour-scale benchmarks.
-
Veda: Scalable Video Diffusion via Distilled Sparse Attention
Veda formulates tile selection in video diffusion attention as a reconstruction problem from full attention maps, using statistics-aware and head-aware scoring to enable high sparsity with maintained quality and hardw...
-
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
LiveVLM introduces VSB and PaR to compress and retrieve KV cache in streaming video LLMs, enabling LLaVA-OneVision to reach SOTA accuracy among training-free query-agnostic and training-based online models.
-
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on l...
-
CABLE: Cloud-Assisted Bandwidth-efficient LMM-based Encoding for V2X Systems
CABLE uses ego-motion compensated prior masks refined by residual cues and corridor envelopes to select ROIs for cloud LMM inference, cutting pixel upload 73-87% with 5-8x prefill speedup and modest quality loss acros...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.