HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention proposes a two-stage hierarchical indexer that replaces the flat token scan used in token-level sparse attention mechanisms like DeepSeek Sparse Attention. The method first performs block-level coarse filtering to discard irrelevant regions, then applies the original token-level indexer only within the retained candidate blocks, preserving the same top-sparse pattern for downstream attention. Benchmarks show HISA achieves significant speedups at 64K context and matches the quality of DeepSeek-V3.2 and GLM-5 without additional training.
By Yufei Xu, Fanxu Meng, Fan Jiang, Yuxuan Wang, Ruijie Zhou, Zhaohui Wang, Jiexi Wu, Zhixin Pan, Xiaojuan Tang, Wenjie Pei, Tongxuan Liu, Di Yin, Xing Sun, Muhan Zhang
arXiv:2610.42147v1 Announce Type: new
Abstract: Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context wind...
By Ales Kubicek, Andrea Caciolai, Liangzu Peng, Sukrit Sumant, Benjamin Hoover, Fraser Greenlee, Ruairidh M. Battleday, Radim Urban, Torsten Hoefler, James C. R. Whittington
arXiv:2607. 11976v1 Announce Type: new Abstract: Indexer-TopK, the operation to compute the scores and select the top-k candidates, is widely used by sparse attention kernels in large language models and vector retrieval in recommendation systems and vector databases.
By Ziqi Yin, Jianyang Gao, Peiqi Yin, Jiangneng Li, Gao Cong
HyScale is a long‑context training system designed to accelerate learned sparse attention for million‑token contexts. It introduces HyTopK, which computes each query’s exact top‑k indices on the fly without a full score table, and selection replay, which reuses forward‑pass selections during recomputation. These techniques, combined with system‑wide optimizations, achieve a 2.07× speedup for GLM‑5.1 training on 1M‑token sequences compared to Megatron‑LM, and similar gains for DeepSeek‑V4‑Flash and Qwen3.8‑Flash‑Next on large GPU clusters.
By Yangsheng Deng, Xinjing Huang, Yulong Wang, Yunzhuo Liu, Jun Hu, Shuyong Tang, Junchi Zeng, Mingji Han, Ray Ying, Key Zhang, Luo Mai
arXiv:2610.27438v1 Announce Type: cross
Abstract: Sparse attention limits the keys used by each query, but finding those keys can still require a full-prefix scan at every layer. We introduce \textbf...
By Samkit Jain, Sai Kishan Pampana, Shlok Agarwal
arXiv:2606. 09441v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) injects LLM queries with relevant documents to improve response quality.
By Rya Sanovar, Srikant Bharadwaj, Hritvik Taneja, Moinuddin Qureshi
arXiv:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.
By Wenshuai Yao, Wenyong Zhou, Hanyong Shao, Yizhe Chen, Zhiyuan Ning, Yuannuo Feng, Ru Huang, Kechao Tang
The paper introduces Stratified Sparse Attention (SSA), a framework that blends deterministic top‑k retrieval with score‑guided sampling to reduce the gap between sparse and dense attention in large language models. SSA attends to high‑scoring tokens deterministically while sampling the remaining attention mass using proxy scores, thereby recovering more of the attention distribution. Experiments on benchmarks such as RULER, LongBench, LOFT, and AIME show that SSA outperforms existing sparse methods across models ranging from 3B to 27B parameters, achieving significant accuracy gains and up to 2.96× decode speedup with optimized CUDA kernels.
By Sahil Joshi, Prithvi Dixit, Aryan Katiyar, Agniva Chowdhury, Joseph E. Gonzalez, Anshumali Shrivastava, Aditya Desai, Kumar Krishna Agrawal
Block Sparse Flash Attention (BSFA) is a drop‑in replacement for FlashAttention that speeds up long‑context inference by pruning about 50% of computation and memory transfers. It selects the top‑k most important value blocks for each query using exact query‑key similarities and calibrated per‑layer, per‑head thresholds, requiring only a one‑time training‑free calibration. On Llama‑3.1‑8B, BSFA delivers up to 1.13× speedup on LongBench with a 1.1% accuracy drop and up to 1.24× on Needle‑in‑a‑Haystack retrieval with a 1% drop, while the attention kernel itself accelerates by up to 1.38×.
By Daniel Ohayon, Itay Lamprecht, Itay Hubara, Israel Cohen, Daniel Soudry, Noam Elata
The paper introduces OpenAttention, a sparse attention framework that uses a single count‑aware mean proxy to represent the unread tail of the key‑value cache, outperforming sampling methods at low read rates. It combines clustering, an ErrorGate that allocates reads based on estimated weight error, and a query‑geometry selector to efficiently compress keys while preserving query direction. Experiments on RULER‑32K HARD with Llama‑3.1‑8B show OpenAttention retains 99 % of dense accuracy at a 1 % read and achieves state‑of‑the‑art accuracy across models, contexts, and datasets, with a custom kernel that is ten times faster than dense attention at the same read rate.
By Hyunwoo Yu, Jongbeom Lee, Hyunbin Kim, Sungjun Park, Jaemin Choi, Jincheol Yang, Seunghun Moon, Bongjoon Hyun, Kyomin Sohn, Kyeongbo Kong, Suk-Ju Kang
arXiv:2504. 17768v3 Announce Type: replace-cross Abstract: Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency-accuracy trade-offs remain unclear due to the lack of comprehensive evaluation.
By Piotr Nawrot, Robert Li, Renjie Huang, Sebastian Ruder, Kelly Marchisio, Edoardo M. Ponti
CRISP (Cliff-awaRe Input-adaptive Sparse Prefilling) is a new method for long-context LLM inference that replaces costly quadratic attention prefilling with a dynamic, input-adaptive sparse routing scheme. It introduces a structural proxy, C_struct, to directly read routing decisions from the proxy attention map, eliminating the need for pooled matrix multiplication and KL divergence. Additionally, CRISP addresses the post-softmax mass cliff by using a sink-aware threshold based on the noise floor, theoretically reducing background noise accumulation to O(n). Empirical results on InfiniteBench, RULER, and LongBench show that CRISP outperforms existing sparse methods and can match or exceed exact dense attention, achieving up to a 5.30× speedup at 512k tokens and significant gains on retrieval-heavy tasks.
By Huu Huy Nguyen, Chien Van Nguyen, Franck Dernoncourt, Ryan A. Rossi, Linh Ngo Van, Jieyang Chen, Thien Huu Nguyen