Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods improve efficiency but sacrifice precision. We propose AsyncTLS, a hierarchical sparse attention system that combines coarse-grained block filtering with fine-grained token selection to balance accuracy and efficiency, coupled with an asynchronous offloading engine that overlaps KV cache transfers with computation via temporal locality exploitation. Evaluated on Qwen3 and GLM-4.7-Flash across GQA, and MLA architectures, AsyncTLS achieves accuracy comparable to full attention while delivering 1.2x - 10.0x operator speedups and 1.3x - 4.7x end-to-end throughput improvements on 48k - 96k contexts.
@article{arxiv.2604.07815,
title = {AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention},
author = {Yuxuan Hu and Jianchao Tan and Jiaqi Zhang and Wen Zan and Pingwei Sun and Yifan Lu and Yerui Sun and Yuchen Xie and Xunliang Cai and Jing Zhang},
journal= {arXiv preprint arXiv:2604.07815},
year = {2026}
}