Newest papers

Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity

Sahil Joshi, Prithvi Dixit, Aryan Katiyar, Agniva Chowdhury, Joseph E. Gonzalez, Anshumali Shrivastava, Aditya Desai, Kumar Krishna Agrawal · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28441 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

長い文脈にわたって大規模なコード・トランペア・モデル・オープン・インテリジェンスは、長い文脈にわたって長期的なキー・バリエンス(KV)キャッシュに従事するコストによってますますボトルネックされています。 Sparse 注意は、キャッシュのほんの一部にアクセスすることによりこのコストを削減しますが、既存の方法は、強力なスパルシティーで密集した注意から大規模な注意から大きな差を表しています。我々は、より高いバリエンスのコストでカバーを改善するための統一されたフレームワークを導入します。ハイブリッド・メソッドは、トップ$k$のキャッシュと均一なサンプリングを組み合わせますが、依然として、攻撃

Machine translation (Meta M2M100); the English original follows.

Abstract

Large Language Model inference over long contexts is increasingly bottlenecked by the cost of attending to a growing Key-Value (KV) cache. Sparse attention reduces this cost by accessing only a fraction of the cache, but existing methods face a trade-off between deterministic retrieval, which captures high-scoring tokens but discards residual attention mass, and sampling, which improves coverage at the cost of higher variance. Hybrid methods combine top-$k$ retrieval with uniform sampling, yet still exhibit a substantial gap from dense attention at aggressive sparsity. We introduce \emph{Stratified Sparse Attention (SSA)}, a unified framework combining deterministic retrieval with score-guided sampling. SSA deterministically attends to high-scoring tokens while sampling the residual using proxy attention scores and correcting for their inclusion probabilities, thereby recovering attention mass beyond the retrieval set. SSA encompasses top-$k$, top-$p$, and hybrid top-$k$+sampling as special cases. Across RULER, LongBench, LOFT, and AIME, and five models ranging from 3B to 27B parameters, SSA consistently improves over the baselines at matched sparsity. On RULER-HARD with Ministral-3-8B, SSA improves accuracy over the strongest practical baseline from 81.8\% to 84.2\% at 32K and from 63.8\% to 69.3\% at 128K under $50\times$ attention sparsity, recovering 94\% and 85\% of dense-attention performance, respectively. With optimized CUDA kernels, SSA achieves up to $2.96\times$ decode speedup over FlashInfer at 1M context, demonstrating that its accuracy gains translate into practical long-context inference acceleration. We open-source our code at https://github.com/skylight-org/SSA-Paper-Code.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Inference, Residual, Ranging, Speedup, Proxy (statistics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange