paper-with-me

Papers

Transformer-VQ: Linear-Time Transformers via Vector Quantization

2023-09-28 · Lucas D. Lingle

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}

📄 PDF Abstract BibTeX arXiv:2309.16354

Code (1)

transformer-vq/transformer_vq 공식 구현 jax

Tasks

8kDecoderQuantization

Similar Papers 제목 키워드 기반

GT-SVQ: A Linear-Time Graph Transformer for Node Classification Using Spiking Vector Quantization

2025-04-16 · Huizhe Zhang, Jintang Li, Yuchang Zhu, Liang Chen 외

Graph Transformers (GTs), which simultaneously integrate message-passing and self-attention mechanisms, have achieved promising empirical results in some graph prediction tasks. Although these approaches show the potenti…

Graph LearningGraph Representation LearningNode ClassificationQuantization+1

ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers

2025-12-03 · Feice Huang, Zuliang Han, Xing Zhou, Yihuang Chen 외 arxiv

Diffusion transformers have demonstrated strong capabilities in generating high-quality images. However, as model size increases, the growing memory footprint and inference latency pose significant challenges for practic…

Mixed Non-linear Quantization for Vision Transformers

2024-07-26 · Gihwan Kim, Jemin Lee, Sihyeong Park, Yongin Kwon 외

The majority of quantization methods have been proposed to reduce the model size of Vision Transformers, yet most of them have overlooked the quantization of non-linear operations. Only a few works have addressed quantiz…

Quantization

Exploring Quantization for Efficient Pre-Training of Transformer Language Models

2024-07-16 · Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, Sarath Chandar

The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training and during fine-tuning, applying quanti…

Language ModelingLanguage ModellingQuantization

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

2024-08-30 · Juncan Deng, Shuaiting Li, Zeyu Wang, Hong Gu 외

The Diffusion Transformers Models (DiTs) have transitioned the network architecture from traditional UNets to transformers, demonstrating exceptional capabilities in image generation. Although DiTs have been widely appli…

GPUImage GenerationQuantizationVideo Generation