Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2309.16354 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- 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}