Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$ attention mechanisms have been proposed to accelerate LLM inference by exploiting the inherent sparsity of attention, they often struggled to strike a balance between efficiency and accuracy. In this paper, we introduce HATA (Hash-Aware Top-$k$ Attention), a novel approach that systematically integrates low-overhead learning-to-hash techniques into the Top-$k$ attention process. Different from the existing top-k attention methods which are devoted to seeking an absolute estimation of qk score, typically with a great cost, HATA maps queries and keys into binary hash codes, and acquires the relative qk score order with a quite low cost, which is sufficient for realizing top-k attention. Extensive experiments demonstrate that HATA achieves up to 7.2$\times$ speedup compared to vanilla full attention while maintaining model accuracy. In addition, HATA outperforms the state-of-the-art top-$k$ attention methods in both accuracy and efficiency across multiple mainstream LLM models and diverse tasks. HATA is open source at https://github.com/gpzlx1/HATA.
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference
HATA, a hash-aware top-k attention mechanism, significantly accelerates LLM inference by converting queries and keys into binary hash codes, achieving high speedup and maintaining accuracy.
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 16
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2506.02572ARXIV-DEFAULT
- TL;DR
- Semantic Scholar