LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2502.02406v2
• Date: Thu, 06 Feb 2025 19:50:41 GMT
• Title: LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models
• Authors: Tzu-Tao Chang, Shivaram Venkataraman,
• Abstract summary: We propose LV-XAttn, a distributed, exact cross-attention mechanism with minimal communication overhead. We show that LV-XAttn achieves up to 5.58$times$ end-to-end speedup compared to existing approaches.
• Score: 1.3943553944889038
• License:
• Abstract: Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a large number of visual tokens in cross-attention layers leads to high memory demands and often necessitates distributed computation across multiple GPUs. Existing distributed attention mechanisms face significant communication overheads, making cross-attention layers a critical bottleneck for efficient training and inference of MLLMs. To address this, we propose LV-XAttn, a distributed, exact cross-attention mechanism with minimal communication overhead. We observe that in applications involving large visual inputs the size of the query block is typically much smaller than that of the key-value blocks. Thus, in LV-XAttn we keep the large key-value blocks locally on each GPU and exchange smaller query blocks across GPUs. We also introduce an efficient activation recomputation technique enabling support for longer visual context. We theoretically analyze the communication benefits of LV-XAttn and show that it can achieve speedups for a wide range of models. Our evaluations with mPLUG-Owl3 and OpenFlamingo models find that LV-XAttn achieves up to 5.58$\times$ end-to-end speedup compared to existing approaches.

Related papers

• HiMix: Reducing Computational Complexity in Large Vision-Language Models [16.33839330391886]
  We argue that one main bottleneck in computational complexity is caused by the involvement of redundant vision sequences in model computation. We propose a novel hierarchical vision-language interaction mechanism called Hierarchical Vision injection for Mixture Attention (HiMix) In HiMix, only the language sequence undergoes full forward propagation, while the vision sequence interacts with the language at specific stages within each language decoder layer.
  arXiv  Detail & Related papers  (2025-01-17T17:41:47Z)
• Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference [14.805702987440512]
  We introduce Flash Communication, a novel low-bit compression technique designed to alleviate the tensor-parallelism communication bottleneck during inference. Our method substantially boosts intra-node communication speed by more than 3x and reduces the time-to-first-token by 2x, with nearly no sacrifice in model accuracy.
  arXiv  Detail & Related papers  (2024-12-06T11:29:32Z)
• A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs [65.00970402080351]
  A promising approach to accelerating large vision-language models (VLMs) is using partial information, such as attention maps from specific layers, to assess token importance and prune less essential tokens. Our study reveals three key insights: (i) Partial attention information is insufficient for accurately identifying critical visual tokens, resulting in suboptimal performance, especially at low token retention ratios; (ii) Global attention information, such as the attention map aggregated across all layers, more effectively preserves essential tokens and maintains comparable performance under aggressive pruning; and (iii) The global attention map aggregated from a small VLM closely resembles that of a large VLM,
  arXiv  Detail & Related papers  (2024-12-04T13:56:44Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE) DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• Anchor Attention, Small Cache: Code Generation with Large Language Models [15.94784908771546]
  Current practices in NLP often use sparse attention which may, unfortunately, lead to substantial inaccuracies, or hallucinations, in code generation tasks. We propose a novel approach, AnchorCoder, which features token-wise anchor attention designed to extract and compress contextual information. It can consistently achieve a significant (at least 70%) reduction in KV cache requirements, while preserving the majority of model's performance.
  arXiv  Detail & Related papers  (2024-11-11T02:47:05Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• X-VILA: Cross-Modality Alignment for Large Language Model [91.96081978952283]
  X-VILA is an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. We propose a visual alignment mechanism with a visual embedding highway module to address the problem of visual information loss. X-VILA exhibits proficiency in any-to-any modality conversation, surpassing previous approaches by large margins.
  arXiv  Detail & Related papers  (2024-05-29T17:59:58Z)
• Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference [59.91176945361035]
  We introduce Visual Tokens Withdrawal (VTW), a plug-and-play module to boost MLLMs for rapid inference. VTW strategically withdraws vision tokens at a certain layer, enabling only text tokens to engage in subsequent layers. Our approach can cut computational overhead by over 40% across diverse multimodal tasks while maintaining performance.
  arXiv  Detail & Related papers  (2024-05-09T14:38:53Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention [100.81495948184649]
  We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Our framework scales with linear complexity, in contrast to the quadratic complexity of self-attention used in many state-of-the-art transformer-based models.
  arXiv  Detail & Related papers  (2022-11-21T18:22:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.