# Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding Source: [Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding]() Collection index: [llms.txt]() Data updated: 2025-10-27T07:01:39.647Z Authors: Mingxiao Huo, Jiayi Zhang, Hewei Wang, Jinfeng Xu, Zheyu Chen, Huilin Tai, Yijun Chen Published: 2025-09-15T14:16:51.000Z ## Abstract 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 speculative decoding to accelerate VLMs without sacrificing output quality. Spec-LLaVA pairs a lightweight draft VLM with a large target model: the draft speculates future tokens, which the target verifies in parallel, allowing multiple tokens to be generated per step. To maximize efficiency, we design a dynamic tree-based verification algorithm that adaptively expands and prunes speculative branches using draft model confidence. On MS COCO out-of-domain images, Spec-LLaVA achieves up to 3.28$\\times$ faster decoding on LLaVA-1.5 (7B, 13B) with no loss in generation quality. This work presents a lossless acceleration framework for VLMs using dynamic tree-structured speculative decoding, opening a path toward practical real-time multimodal assistants. Importantly, the lightweight draft model design makes the framework amenable to resource-constrained or on-device deployment settings. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()