# DistrAttention: An Efficient and Flexible Self-Attention Mechanism on Modern GPUs

arXiv: https://arxiv.org/abs/2507.17245 · HTML: https://mlsanity.com/paper/2507.17245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [FLatten Transformer: Vision Transformer using Focused Linear Attention](https://mlsanity.com/paper/2308.00442/) (2023)
- [Primer: Searching for Efficient Transformers for Language Modeling](https://mlsanity.com/paper/2109.08668/) (2021)
- [Agent Attention: On the Integration of Softmax and Linear Attention](https://mlsanity.com/paper/2312.08874/) (2023)
- [TensorFlow-Serving: Flexible, High-Performance ML Serving](https://mlsanity.com/paper/1712.06139/) (2017)
- [HyperAttention: Long-context Attention in Near-Linear Time](https://mlsanity.com/paper/2310.05869/) (2023)
- [Hydra Attention: Efficient Attention with Many Heads](https://mlsanity.com/paper/2209.07484/) (2022)
- [A Survey on Transformer Compression](https://mlsanity.com/paper/2402.05964/) (2024)
- [Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation](https://mlsanity.com/paper/2305.19798/) (2023)
- [Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey](https://mlsanity.com/paper/2405.00314/) (2024)

## Abstract (arXiv)

The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time series prediction. However, its core component, self-attention, has the quadratic time complexity relative to input sequence length, which hinders the scalability of Transformers. The exsiting approaches on optimizing self-attention either discard full-contextual information or lack of flexibility. In this work, we design DistrAttention, an effcient and flexible self-attention mechanism with the full context. DistrAttention achieves this by grouping data on the embedding dimensionality, usually referred to as d. We realize DistrAttention with a lightweight sampling and fusion method that exploits locality-sensitive hashing to group similar data. A block-wise grouping framework is further designed to limit the errors introduced by locality sensitive hashing. By optimizing the selection of block sizes, DistrAttention could be easily integrated with FlashAttention-2, gaining high-performance on modern GPUs. We evaluate DistrAttention with extensive experiments. The results show that our method is 37% faster than FlashAttention-2 on calculating self-attention. In ViT inference, DistrAttention is the fastest and the most accurate among approximate self-attention mechanisms. In Llama3-1B, DistrAttention still achieves the lowest inference time with only 1% accuray loss.