SQAP-VLA：一种面向高性能视觉-语言-动作模型的协同量化感知剪枝框架
SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
AI总结：
SQAP-VLA提出首个无需训练的VLA推理加速框架，协同设计量化与令牌剪枝，实现1.93倍加速和最高4.5%成功率提升。
摘要：
视觉-语言-动作（VLA）模型展现出前所未有的具身智能能力。然而，其庞大的计算和内存开销阻碍了实际部署。现有的VLA压缩与加速方法以临时方式分别进行量化或令牌剪枝，但由于观察到的不兼容性，无法同时实现两者以获得整体效率提升。本工作提出SQAP-VLA，这是首个结构化、无需训练的VLA推理加速框架，可同时实现最先进的量化与令牌剪枝。我们通过协同设计量化与令牌剪枝流程来克服不兼容性，其中我们提出了新的量化感知令牌剪枝标准，该标准适用于激进量化模型，同时改进量化器设计以增强剪枝效果。当应用于标准VLA模型时，SQAP-VLA在计算效率和推理速度方面带来显著提升，同时成功保持核心模型性能，实现了1.93倍加速，相较于原始模型平均成功率提升高达4.5%。
英文摘要：
Vision-Language-Action (VLA) models exhibit unprecedented capabilities for embodied intelligence. However, their extensive computational and memory costs hinder their practical deployment. Existing VLA compression and acceleration approaches conduct quantization or token pruning in an ad-hoc manner but fail to enable both for a holistic efficiency improvement due to an observed incompatibility. This work introduces SQAP-VLA, the first structured, training-free VLA inference acceleration framework that simultaneously enables state-of-the-art quantization and token pruning. We overcome the incompatibility by co-designing the quantization and token pruning pipeline, where we propose new quantization-aware token pruning criteria that work on an aggressively quantized model while improving the quantizer design to enhance pruning effectiveness. When applied to standard VLA models, SQAP-VLA yields significant gains in computational efficiency and inference speed while successfully preserving core model performance, achieving a $\times$1.93 speedup and up to a 4.5\% average success rate enhancement compared to the original model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
