Representation Shift: Unifying Token Compression with FlashAttention
This addresses the computational and memory overhead in Transformers for tasks like video processing, though it is incremental as it builds on existing token compression and FlashAttention techniques.
The paper tackles the incompatibility between token compression methods and FlashAttention by proposing Representation Shift, a training-free metric that measures token representation changes, enabling effective compression with FlashAttention and achieving speedups of up to 5.5% in video-text retrieval and 4.4% in video QA.
Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory access. To reduce the computation cost of self-attention, prior work has proposed token compression techniques that drop redundant or less informative tokens. Meanwhile, fused attention kernels such as FlashAttention have been developed to alleviate memory overhead by avoiding attention map construction and its associated I/O to HBM. This, however, makes it incompatible with most training-free token compression methods, which rely on attention maps to determine token importance. Here, we propose Representation Shift, a training-free, model-agnostic metric that measures the degree of change in each token's representation. This seamlessly integrates token compression with FlashAttention, without attention maps or retraining. Our method further generalizes beyond Transformers to CNNs and state space models. Extensive experiments show that Representation Shift enables effective token compression compatible with FlashAttention, yielding significant speedups of up to 5.5% and 4.4% in video-text retrieval and video QA, respectively. Code is available at https://github.com/mlvlab/Representation-Shift.