EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
This work addresses efficiency bottlenecks in embodied AI for robotics and autonomous systems, representing an incremental improvement over existing quantization methods.
The paper tackles the high computational and storage costs of Vision-Language-Action (VLA) models by proposing EaqVLA, an encoding-aligned quantization framework that addresses token alignment issues, achieving minimal quantization loss and acceleration.
With the development of Embodied Artificial intelligence, the end-to-end control policy such as Vision-Language-Action (VLA) model has become the mainstream. Existing VLA models faces expensive computing/storage cost, which need to be optimized. Quantization is considered as the most effective method which can not only reduce the memory cost but also achieve computation acceleration. However, we find the token alignment of VLA models hinders the application of existing quantization methods. To address this, we proposed an optimized framework called EaqVLA, which apply encoding-aligned quantization to VLA models. Specifically, we propose an complete analysis method to find the misalignment in various granularity. Based on the analysis results, we propose a mixed precision quantization with the awareness of encoding alignment. Experiments shows that the porposed EaqVLA achieves better quantization performance (with the minimal quantization loss for end-to-end action control and xxx times acceleration) than existing quantization methods.