paper-with-me

Papers

On Speculative Decoding for Multimodal Large Language Models

2024-04-13 · Mukul Gagrani, Raghavv Goel, Wonseok Jeon, Junyoung Park, Mingu Lee, Christopher Lott

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of speculative decoding to enhance the inference efficiency of MLLMs, specifically the LLaVA 7B model. We show that a language-only model can serve as a good draft model for speculative decoding with LLaVA 7B, bypassing the need for image tokens and their associated processing components from the draft model. Our experiments across three different tasks show that speculative decoding can achieve a memory-bound speedup of up to 2.37$\times$ using a 115M parameter language model that we trained from scratch. Additionally, we introduce a compact LLaVA draft model incorporating an image adapter, which shows marginal performance gains in image captioning while maintaining comparable results in other tasks.

📄 PDF Abstract BibTeX arXiv:2404.08856

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningLanguage ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

MMSpec: Benchmarking Speculative Decoding for Vision-Language Models

2026-03-16 · Hui Shen, Xin Wang, Ping Zhang, Yunta Hsieh 외 arxiv

Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculative decoding has recently emerged as an e…

Speculative Decoding Reimagined for Multimodal Large Language Models

2025-05-20 · Luxi Lin, Zhihang Lin, Zhanpeng Zeng, Rongrong Ji

This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrifi…

Language ModelingLanguage Modelling

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding

2025-05-25 · Yunhai Hu, Tianhua Xia, Zining Liu, Rahul Raman 외

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We intr…

feature selection

Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding

2025-09-15 · Mingxiao Huo, Jiayi Zhang, Hewei Wang, Jinfeng Xu 외 arxiv

Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce Spec-LLaVA, a system that applies specul…

Multimodal Reasoning

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding

2025-09-17 · Jialiang Kang, Han Shu, Wenshuo Li, Yingjie Zhai 외 arxiv

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving o…