Transformer-VQ: Linear-Time Transformers via Vector Quantization

ICLR 2025 Conference Submission393 Authors

Keywords: Transformer, Transformer Decoder, Decoder-Only Transformer, Natural Language Processing, NLP, Vector Quantization, VQ, K-Means, Clustering, Causal Attention, Autoregressive Attention, Efficient Attention, Linear-Time Attention, Autoregressive Modeling, Generative Modeling, Gated Attention, Compressive Attention, Kernelized Attention, Kernelizable Attention, Hierarchical Attention, Segment-Level Recurrent Attention, Long-Context Modeling, Long-Range Modeling, Long-Range Dependencies, Long-Term Dependencies, Cached Attention, Shift-Equivariant Attention

Abstract:

We introduce Transformer-VQ, a decoder-only transformer computing softmax-based dense self-attention in linear time. Transformer-VQ's efficient attention is enabled by vector-quantized keys and a novel caching mechanism.
In our large-scale experiments, Transformer-VQ is shown highly competitive in quality, obtaining 0.99 bpb on Enwik8, 26.6 ppl on PG-19, and 3.16 bpb on ImageNet64. In addition, the optimized implementation of Transformer-VQ is over 3x faster than a comparable quadratic-time transformer at sequence length 8k, is over 12x faster at 32k, and can scale to 131k with similar throughput. Code available: \url{https://github.com/transformer-vq/transformer_vq}

Submission Number: 393