This paper proposes Block-Filtered Long-Context Attention (BFLA), a training-free sparse prefill attention mechanism for long-context inference. BFLA adopts a two-stage design. In Stage 1, query and key sequences are compressed into coarse blocks, and lightweight block-level softmax mass estimation is performed to construct an input-dependent block importance mask. In Stage 2, the coarse mask is expanded to the Triton attention-tile grid. Several tile-level rescue strategies are applied to reduce information loss, where a fused sparse prefill kernel skips unimportant KV tiles while preserving exact token-level attention inside every retained tile. BFLA requires no retraining, calibration, preprocessing, or model modification and can be plugged into existing vLLM-style paged-attention workloads. Experiments on Gemma 4, Llama 3.1, Qwen 3.5, and Qwen 3.6 series models show that BFLA substantially accelerates long-context prefilling with minimal accuracy degradation compared to dense Triton FlashAttention. Project website: https://github.com/Alicewithrabbit/BFLA.
Cite
@article{arxiv.2605.12193,
title = {BFLA: Block-Filtered Long-Context Attention Mechanism},
author = {Chong Wu and Zhenan Feng and Renjie Xu and Houwang Zhang and Jiawang Cao and Maolin Che and Wenbo Zhu and Hong Yan},
journal= {arXiv preprint arXiv:2605.12193},
year = {2026}
}