SyncAI.news, a Varaisys broadcasting
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
QQ

Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang, Kebin Liu, Qingqing Dang, Juntao Li, Min Zhang

· 1 min read

ResearcharXiv cs.CL

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

arXiv:2604.07394v2 Announce Type: replace-cross Abstract: The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8$\times$A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to $2.8\times$ and $2.0\times$ in the prefill and decode stages.

Original source

This story was published by arXiv cs.CL and written by Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang, Kebin Liu, Qingqing Dang, Juntao Li, Min Zhang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News