Sparse Attention

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 160

Jul 3, 2026cs.CL

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse attention offers a promising alternative, but all existing methods fall short of full attention because of their inaccurate chunk selection. We propose Hierarchical Landmark Sparse (HiLS) Attention, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling (LM) loss. HiLS factorizes attention hierarchically: each query performs attention independently with each retrieved chunk to extract chunk-specific information, and the resulting outputs are fused according to chunk retrieval scores. By incorporating retrieval scores into the forward attention computation, HiLS optimizes them directly with the LM loss, enabling end-to-end retrieval learning and native sparse training. Experimental results show that HiLS-Attention achieves performance comparable to, and in some cases better than, full attention at in-domain context lengths. Meanwhile, HiLS-Attention extrapolates more than

64\times

the training context length with 90% retrieval accuracy, far beyond full attention. Moreover, existing full-attention models can be converted to HiLS-Attention with lightweight continued pretraining, preserving in-domain performance while acquiring ultra-long-context extrapolation. Together with its sparse KV access and computation, HiLS-Attention breaks the usual efficiency-performance trade-off, enabling long-context LLMs that are both more efficient and more effective on general long-context tasks than their full-attention counterparts.

Xiang Hu, Xinyu Wei, Hao Gu +10

Tencent HY Team · ShanghaiTech University · The Hong Kong University of Science and Technology +1

Long-Context Language Model Inference Long-Context Language Modeling Long-Context Modeling Sparse Attention

Jul 1, 2026cs.CL

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale

Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant answer. However, prior work has largely focused on proprietary systems or the smaller-scale reranking task, leaving corpus-scale in-context retrieval largely unexplored. In this work, we present the first systematic study of in-context retrieval on two scales practical retrievers demand: million-token corpora and length-generalization far beyond training-time sizes. We first introduce BlockSearch, a 0.6B LM retriever whose architectural and training modifications improve over prior LM baselines and length-generalize up to 10 times beyond its training regime. Nevertheless, retrieval still collapses under more extreme extrapolation. We trace this failure to an attention dilution effect: as the corpus grows, irrelevant documents dominate the softmax denominator, reducing the normalized mass on the gold document even when its pre-softmax score stays high. Motivated by this analysis, we introduce length-aware adjustments to the attention softmax and document-level sparse attention. With these modifications, at the million-token scale, our model matches dense retrieval on widely studied benchmarks (e.g, MS MARCO and NQ), while outperforming the concurrent model MSA despite being 7 times smaller. Furthermore, it significantly outperforms dense retrieval on tasks requiring entirely different notions of similarity, such as LIMIT, achieving a 3 times higher score. Together, our results position in-context retrieval a promising alternative to classical retrieval while emphasizing attention control under extreme context growth as a new challenge.

Siddharth Gollapudi, Nilesh Gupta, Prasann Singhal +1

UC Berkeley · UT Austin

In-Context Retrieval Length Generalization Long-Context Modeling Sparse Attention

Jun 30, 2026cs.LG

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budget (Top-k) retrieval or rely on proxy scores that are computationally expensive and biased. To address these limitations, we propose RaBitQCache, a novel sparse attention framework that utilizes randomized rotated binary quantization and high-throughput binary-INT4 arithmetic to efficiently estimate attention weights. Our proxy score serves as an unbiased estimator with a proven error bound, enabling adaptive Top-p retrieval that dynamically adjusts the token budget based on actual attention sparsity. We further implement a hardware-aware system with asynchronous pipelining and lazy updates to mask overhead. Evaluations demonstrate that RaBitQCache significantly accelerates inference and reduces memory I/O while preserving generation quality compared to state-of-the-art baselines. Code is available at https://github.com/Sakuraaa0/RaBitQCache.git.

Wenhao Li, Jinhao Dong, Hailin Zhang +3

School of Information, Renmin University of China, Beijing, China · Peking University, Beijing, China

KV Caching Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Quantization

Jun 30, 2026cs.CV

Dual Sparse Aggregation Transformer for Multispectral Object Detection

Transformer-based approaches have obtained excellent performance in multispectral object detection tasks due to their ability to model long-range dependencies and capture complementary information. However, previous transformer-based multispectral detection methods tend to use all available tokens for similarity calculation, which results in redundant information interaction from irrelevant areas, leading to degraded detection performance. To overcome this challenge, we propose a novel Dual Sparse Aggregation Transformer (DSAFormer) for multispectral object detection, which consists of a Dual Sparse Transformer (DSFormer) and a Learnable Addition Fusion Block (LAFB). Specifically, the DSFormer is designed to exploit and boost cross-modal complementary information, thereby improving detection performance. It incorporates three key components: A Spatial Sparse Multi-Head Cross-Attention (SSMHCA) mechanism selectively captures cross-modal relationships at the spatial level by reserving only the high query-key similarity scores, eliminating irrelevant interactions. A Channel Sparse Multi-Head Cross-Attention (CSMHCA) mechanism performs similar sparse calculations at the channel level to enhance feature representation and filter out low matching query-key. A Multi-Scale Feature Refinement Layer (MSFRL) is developed to aggregate hierarchical features and suppress redundant information. To effectively fuse multimodal features, the LAFB is introduced to aggregate intramodal and intermodal feature information by feature reweighting. Extensive experimental results have demonstrated that our proposed DSAFormer achieves better detection performance against state-of-the-art methods on four public datasets, including the MFAD, FLIR, M

^3

FD, and LLVIP. The source code of our DSAFormer will be released at https://github.com/WenCongWu/DSAFormer.

Wencong Wu, Xiuwei Zhang, Hanlin Yin +2

School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China · School of Computer Science, the Shaanxi Provincial Key Laboratory of Speech and Image Information Processing and the National Engineering Laboratory for Integrated Aerospace-Ground-Ocean Big Data Application Technology, Northwestern Polytechnical University, Xi’an 710072, China · School of Cybersecurity, Northwestern Polytechnical University, Xi’an 710072, China

Multispectral Object Detection Detection Transformer Sparse Attention Multimodal Fusion

Jun 29, 2026cs.LG

Hierarchical Global Attention (HGA)

Hierarchical Global Attention (HGA) is a drop-in replacement for dense causal attention in pretrained long-context transformers. HGA preserves the original checkpoint parameters: the pretrained

W_Q

,

W_K

,

W_V

, and

W_O

projections remain unchanged, no calibration parameters are introduced, and no retraining is required. Applied to Qwen3-30B-A3B-Instruct-2507-FP8 on a single RTX~5090 (32GB), the patched model runs out of the box at a 64K-token context, where token-level K/V storage is not feasible on this hardware. Unlike previous sparse-attention methods, HGA performs hierarchical two-level routing. It first retrieves relevant chunks using compact RoPE-aware summaries and then refines the selection by routing only the most relevant groups before performing exact token-level attention. This hierarchical retrieval significantly reduces the number of fetched tokens while preserving exact attention over the retrieved token set, making RAM- and NVMe-backed storage practical. The full historical token K/V resides in host RAM or NVMe storage, while only a small routed working set is transferred to GPU memory during attention. Consequently, GPU memory consumption depends primarily on model weights and the routed working set rather than on the total context length. Across all tested context lengths (4K - 64K tokens), routed attention remains within approximately

0.01

--

0.02

nats of dense attention while the sparsity used is just about 3%. These results suggest that the approximation introduced by hierarchical routing is small, and that the remaining quality gap is likely dominated by long-context positional encoding rather than by the routing algorithm itself.

Woernle Frank, Fedosov Vladimir, Grinenko Artemiy

BMW Group

KV-Cache Offloading Long-Context Modeling LLM Inference Acceleration Efficient Attention Sparse Attention

Jun 29, 2026cs.LG

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV blocks relevant to each query, but it introduces a serialized selection-to-attention dependency that emerges as a new latency bottleneck. We present PRR, a speculate-reuse-repair runtime that exploits temporal locality in DSA selections to predict likely blocks, speculate the attention over them while selection is in flight, and incrementally repair missed blocks once the true selected set is known. PRR uses a lightweight EMA-based predictor, a profiling-guided speculation budget that keeps speculative work off the critical path, and a FlashAttention-based repair kernel that folds missed blocks into the partial attention state using online-softmax statistics. Across long-context benchmarks and representative DSA methods, PRR reduces per-token decoding latency by up to 40% while preserving downstream task accuracy. Github: https://github.com/Tianyu9748/Incremental_FlashAttention

Tianyu Wang, Gourav Rattihalli, Aditya Dhakal +4

University of Pittsburgh, Pittsburgh, PA, USA · HPE Labs, Milpitas, CA, USA

Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention

Jun 29, 2026cs.CL

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers

The quadratic computational cost of traditional attention mechanisms poses a major bottleneck to the scalability and practical deployment of large language models (LLMs), particularly in long-context scenarios. To improve efficiency, existing approaches often enforce rigid structural constraints such as local attention windows. However, these strategies typically lead to substantial performance degradation on tasks requiring precise long-range recall. In this work, we propose MATCH, a scalable and efficient framework that augments sparsified attention mechanisms with dynamically integrated in-context information through an efficient retrieval system. Empirical results show that MATCH significantly improves the performance of sparse-attention models on both synthetic and real-world natural-language tasks. These findings highlight the versatility of MATCH as a general approach for enhancing in-context retrieval capabilities while maintaining the efficiency benefits of sparse attention architectures.

Linrui Ma, Chun Hei Lo, Xinyu Wang +12

Huawei Canada · McGill University · Université de Montréal +1

In-Context Retrieval Long-Context Language Modeling LLM Inference Acceleration Sparse Attention

Jun 26, 2026cs.CL

Depth-Staggered Fibonacci Spacing for Sparse Attention: Static Schedules Beat Learned Dilation and Extrapolate Where Dense Attention Fails

We study sparse self-attention in which each query attends to a dense local window plus a set of Fibonacci-spaced offsets, with a per-layer scalar alpha that compresses or expands the spacing. Across 21 language models trained under one matched recipe (60M parameters, 512 hidden, 16 layers, 426M tokens), we compare four ways of setting alpha across depth: fixed, per-layer learned, a static linear stagger, and a coprime (anti-gridding) reassignment of that stagger, together with a reach-matched power-of-2 control. Three results stand out. First, a static per-layer stagger improves perplexity over both fixed and learned alpha, and the gain is base-agnostic: applying the same stagger to a power-of-2 base lifts it above fixed Fibonacci and to parity with learned Fibonacci attention. Second, learning per layer is inert: it does not beat the static schedule and costs roughly five times the inference latency. Third, and most consequential, all sparse variants extrapolate to four times their training length with little or no degradation, whereas a recipe-matched dense baseline collapses (perplexity rises by 201% at 4x length); we attribute this to fixed-offset attention only ever querying relative positions seen during training. We also report two honest negatives: at training length the best sparse model has about 26% higher perplexity than the dense baseline, and the staggering gain is uniform across context positions rather than concentrated at long range.

Chad A. Capps

Independent Researcher

Structured Sparsity Long-Context Modeling Sparse Attention

Jun 24, 2026cs.CV

LCG: Long-Context Consistent Image Generation with Sparse Relational Attention

Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyboards, and visual narratives. We propose Long-Context Generation (LCG), a framework for long-context multi-image text-to-image generation, to improve consistency and scalability in long-context multi-image generation. LCG employs the Sparse Relational Attention (SRA) mechanism to selectively attend to core features across extended visual contexts, ensuring that the propagation of semantic and layout information remains computationally tractable. To enforce semantic alignment, we introduce the Routing Consistency Constraint (RCC), which leverages identity-aware masks to align structural patterns across generation branches, effectively mitigating drift in appearance even in complex multi-character scenes. To support training and evaluation in this setting, we construct the Long-Context Consistency Dataset (LCCD), a large-scale synthetic dataset comprising character-centric multi-image sequences spanning varied situational contexts. LCCD contains 600K training sequences and a separate 1K test set, with each sequence containing 6 to 20 images. The experiments demonstrate that LCG outperforms the compared baselines in prompt alignment and character consistency for long-context image generation, including multi-character scenes.

Zihao Wang, Yijia Xu, Haoze Zheng +3

Huazhong University of Science and Technology, China · Peking University, China · Hong Kong University of Science and Technology, Hong Kong

T2I Generation Image Generation Identity-Preserving Image Generation Sparse Attention

Jun 23, 2026cs.CV

Chorus II: Cross-Request Sparsity Reuse for Efficient Image-to-Video Generation

Serving diffusion models for image-to-video generation is computationally expensive, posing significant challenges for large-scale deployment. Real I2V workloads often contain similar requests, such as repeated effect templates, related subjects, and recurring shot layouts. Existing cross-request acceleration methods mainly exploit this redundancy through feature reuse. We observe that similar I2V requests also share highly consistent sparse attention patterns, enabling historical sparse masks to serve as request-conditioned priors with almost no online mask-prediction overhead. We propose a cross-request reuse framework centered on \textbf{sparsity reuse}, with \textbf{feature reuse} as an optional extension safeguarded by a lightweight \textbf{guidance enhancement}. Our sparsity reuse is implemented as shared sparse mask reuse, which reuses high-quality sparse masks from similar historical requests to avoid per-request online mask prediction. Optional feature reuse applies downsampled computation to highly redundant spatiotemporal regions, mitigating boundary artifacts while preserving efficiency gains. Guidance enhancement reinforces image/text conditioning after reuse, mitigating semantic drift and condition-adherence issues. Experiments show that default sparsity reuse configuration preserves generation quality with a \textbf{2.16

\times

} speedup.

Hao Liu, Chenghuan Huang, Hao Liu +6

Sun Yat-sen University · WeChat HPC, Tencent Inc. · WeChat Vision, Tencent Inc.

Image-to-Video Generation Video Diffusion Models Sparse Attention Diffusion Model Inference Acceleration

Jun 23, 2026cs.LG

Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns

Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabilities such as in-context learning are known to emerge abruptly past a certain model scale. In this paper, we show that emergent capabilities arise stochastically throughout training, with larger models acquiring them earlier on average. We demonstrate that the emergence of capabilities such as pattern completion and indirect object identification corresponds to the abrupt learning of task-relevant attention patterns. To isolate this phenomenon, we train transformer models on synthetic linear map and cellular automata datasets, and we show that the difficulty of learning attention patterns depends on context length and pattern sparsity. Moreover, scaling the number of attention heads improves learning efficiency on our synthetic tasks, while increasing the head dimension yields diminishing returns past a minimum capacity. We additionally investigate architectures with alternative attention mechanisms, showing that MLP-Mixer outperforms a transformer on linear map tasks with complex attention patterns. Our findings provide a mechanistic insight into emergence, showing that downstream capabilities arise abruptly due to the intrinsic difficulty of learning sparse attention patterns in transformer models.

Vatsal Baherwani, Zixi Chen, Shikai Qiu +2

New York University

Language Model Scaling Laws Transformer Attention Sparse Attention

Jun 23, 2026cs.CV

VSANet: View-aware Sparse Attention Network for Light Field Image Denoising

Light field (LF) image denoising is challenging due to the high-dimensional structure of LF data. While noise is independent across sub-aperture images, scene content exhibits strong cross-view correlations. We introduce VSANet, a view-aware sparse attention network for LF denoising. Specifically, we propose a view-aware sparse attention (VSA) block that represents the 4D LF feature map as a unified spatial-angular token space and performs cross-view aggregation via locality-sensitive hashing-based sparse attention. This enables global feature interactions with linear complexity, effectively exploiting LF correlations across views and spatial locations. In addition, we design a feature refinement (FR) block to emphasize informative features in spatial, angular, and epipolar subspaces. The VSA and FR blocks are integrated within a sequential attention refinement module, forming the core of VSANet. Experiments demonstrate VSANet outperforms stateof-the-art LF denoising methods.

Gargi Panda, Soumitra Kundu, Saumik Bhattacharya +1

Department of EE, IIT Kharagpur, India · Rekhi Centre of Excellence for the Science of Happiness, IIT Kharagpur, India · Department of E&ECE, IIT Kharagpur, India

Sparse Attention Image Denoising

Jun 23, 2026cs.CL

Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding

While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency. Existing compression methods fail in this regime: static eviction incurs accuracy loss due to saliency shift, while dynamic selection introduces prohibitive computational overhead during the verification path. We propose Dustin, a sparse verification framework designed for long-context speculative decoding. Dustin integrates lookahead signals from the draft model with historical attention from the target model to identify critical tokens with high fidelity across multi-step verification windows. To reduce recomputation latency, this approach further employs a sparse estimation scheme that restricts importance scoring to a minimal subset of attention heads. Evaluations on PG-19 and LongBench with Qwen2.5-72B demonstrate that Dustin achieves a 27.85x speedup in self-attention and a 9.17x end-to-end decoding speedup at a 32k sequence length, all with negligible accuracy degradation.

WenHung Lee, Jian-Jia Chen, Xiaolin Lin +6

National Yang Ming Chiao Tung University · Technische Universität Darmstadt · Cornell University

Long-Context Language Model Inference KV-Cache Management Speculative Decoding LLM Inference Acceleration Sparse Attention

Jun 22, 2026cs.CV

ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers

While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing sparse methods face a dilemma: dynamic pruning suffers from prohibitive runtime overhead and memory fragmentation, while static heuristics fail to capture fine-grained dependencies. In this work, we propose ScalingAttention, a training-free framework grounded in a key inductive bias: while individual activations are input-dependent, the high-mass attention regions for each head rapidly converge to a stable, prompt-agnostic Intrinsic Sparse Topology. This topology is weight-encoded, scale-invariant, and efficient to extract. ScalingAttention decouples topology discovery from sparsity control via: (1) WEST (Weight-Encoded Sparse Topology), which extracts a robust block-sparse prior mask offline to eliminate runtime search; (2) FAST (Fidelity-Aware Sensitivity Tuning), which adaptively tunes head-wise sparsity based on diffusion fidelity requirements. To ensure practical acceleration, we co-design a hardware-aligned bit-wise block-sparse kernel. Experiments on Wan2.1 show up to 1.90X end-to-end speedup with superior fidelity, establishing a new Pareto frontier over state-of-the-art baselines.

Ruiliang Zhou, Xuecheng Wu, Kang He +6

KlingAI Research · Beijing Institute of Technology · NVIDIA +1

Video Diffusion Models Diffusion Transformer Sparse Attention Diffusion Model Inference Acceleration Block-Sparse Attention

Jun 22, 2026cs.LG

SpotAttention: Plug-In Block-Sparse Routing for Pretrained Long-Context Transformers

Long contexts have become standard in pretrained LLMs, yet they remain expensive to run: prefill compute grows quadratically with sequence length, and every decode step re-reads a key-value cache that grows linearly with it. Sparse attention cuts these costs by attending only to a relevant subset of past tokens, but selecting that subset is itself expensive. We present SpotAttention, a lightweight selector that attaches to a frozen pretrained transformer and learns by KL distillation to estimate its attention distribution. The selector picks the top-K keys each query attends to, and because its estimate is a calibrated distribution, a dual top-p rule reads the per-query, per-layer budget directly from it. Across Qwen3 (dense, 4B-32B) and Qwen3.5 (hybrid linear/full attention, 4B-9B), SpotAttention matches dense accuracy at contexts up to 128K tokens, eight times the training length. Decode at L=128K runs 3.9x faster than FlashAttention and 1.8x faster than Twilight, the strongest training-free baseline. Quantizing the selector's K-cache to INT4 or FP4 microscale shrinks it 3.5x at no accuracy cost.

Huzama Ahmad, Se-Young Yun

KAIST

Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention Block-Sparse Attention

Jun 16, 2026cs.CL

ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation

Hybrid architectures combining full attention (FA) and sliding-window attention (SWA) are a promising paradigm for efficient LLM inference. However, existing methods typically rely on hand-crafted rules or simple post-hoc heuristics for FA/SWA allocation and offer limited analysis of the attention behaviors underlying these designs. We propose Controllable Sparsity in Hybrid Attention (ConSA), a framework that learns optimal FA/SWA assignment under a user-specified sparsity target. ConSA employs L0 regularization to learn binary masks selecting between FA and SWA for each attention unit, while an augmented Lagrangian constraint enforces the target sparsity at either layer or KV-head granularity. We evaluate ConSA on two LLMs at the 0.6B and 1.7B scales. Learned allocations consistently outperform rule-based baselines, with KV-head-wise allocation yielding clear gains over layer-wise allocation. The learned patterns place SWA in the bottom layers and concentrate FA into contiguous middle-layer blocks, diverging from evenly interleaved patterns in rule-based methods. This structure persists across model scales, sparsity levels, and allocation granularities, revealing a fine-grained spectrum of intrinsic attention behaviors that underlies the learned allocation.

Yao Chen, Yinqi Yang, Junyuan Shang +6

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · Baidu Inc.

LLM Inference Acceleration Sparse Attention Sliding-Window Attention Hybrid Attention

Jun 15, 2026cs.CV

Training-free sparse attention based on cumulative energy filtering

Sparse attention accelerates Diffusion Transformers (DiTs) for video generation by computing only the important tokens while skipping the rest. The token selection strategy is key to balancing sparsity and accuracy. We formulate the token filtering process as a dual-goal optimization problem: maximizing sparsity and minimizing accuracy degradation. Existing algorithms cannot fulfill both objectives simultaneously. For example, Top-p only considers the accuracy constraint, while Top-k maintains a fixed computational budget but loosens the accuracy constraint. This paper demonstrates that maintaining a fixed recall rate is sufficient for ensuring accuracy, whereas a fixed threshold is suboptimal for reducing computational cost. Therefore, we propose a dynamic thresholding scheme to improve sparsity while maintaining the same level of accuracy. Furthermore, our algorithm is deeply integrated with Flash Attention (FA), eliminating the need for any additional masking computation overhead. Experimental results on Wan 2.2 validate that, compared to the BLASST algorithm which is also integrated with FA, our dynamic thresholding strategy enhances sparsity from 61.42% to 82% with a VBench metric drop of less than 5%. This results in an approximate 15% in attention computation and a

1.61\times

increase in computational efficiency, which is 1.18x higher than that of BLASST.

Chunlu Li, Yixuan Pan, Bai Du +5

Huawei Technologies

Video Diffusion Models Diffusion Transformer Attention Control in Diffusion Models Sparse Attention Diffusion Model Inference Acceleration

Jun 11, 2026cs.AI

MiniMax Sparse Attention

Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale. We introduce MiniMax Sparse Attention (MSA), a blockwise sparse attention built upon Grouped Query Attention (GQA). A lightweight Index Branch scores key-value blocks and independently selects a Top-k subset for each GQA group, enabling group-specific sparse retrieval while maintaining efficient block-level execution; the Main Branch then performs exact block-sparse attention over only the selected blocks. Designed around a principle of simplicity and scalability, MSA is deliberately streamlined, making it straightforward to deploy efficiently across a broad range of GPUs. To translate sparsity into practical speedups, we co-design MSA with a GPU execution path that uses exp-free Top-k selection and KV-outer sparse attention to improve tensor-core utilization under block-granular access. On a 109B-parameter model with native multimodal training, MSA performs on par with GQA while reducing per-token attention compute by 28.4x at 1M context. Paired with our co-designed kernel, MSA achieves 14.2x prefill and 7.6x decoding wall-clock speedups on H800. Our inference kernel is available at: https://github.com/MiniMax-AI/MSA. A production-grade natively multimodal model powered by MSA has been publicly released at: https://huggingface.co/MiniMaxAI/MiniMax-M3.

Xunhao Lai, Weiqi Xu, Yufeng Yang +14

MiniMax · Peking University · NVIDIA +4

GPU Kernel Optimization Long-Context Language Modeling LLM Inference Acceleration Efficient Attention Sparse Attention Block-Sparse Attention

Jun 8, 2026cs.AI

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts. We observe two distinct entropy patterns among attention heads: Rigid Heads, whose entropy stays near zero across input segments, and Dynamic Heads, whose entropy fluctuates significantly. Crucially, the distribution of these types is context-dependent and cannot be predetermined offline. We therefore propose EntropyInfer, a training-free framework that uses attention entropy to adaptively allocate compute at the granularity of individual heads and segments during prefilling. For decoding, we introduce a latent KV cache compression scheme that leverages generated output tokens, rather than prefill tokens alone, to identify and retain the most critical cache entries. Extensive experiments on Llama, Qwen and openPangu model series show that EntropyInfer consistently outperforms baselines including SnapKV, AdaKV, and CritiPrefill, achieving up to 2.39

\times

end-to-end speedup beyond 100k tokens with minimal quality degradation compared to full attention. The code is released in https://github.com/SHA-4096/EntropyInfer.

Zhanchao Xu, Haoyang Li, Qingfa Xiao +4

Department of Computing, PolyU · DSA, HKUST(GZ) · CSE, HKUST

Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Compression

Jun 8, 2026cs.AI

SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance

Retrieval-Augmented Generation (RAG) injects LLM queries with relevant documents to improve response quality. This injection increases prompt length and slows time to first token (TTFT). Unlike standard queries, RAG queries have a unique property of context reuse where the same documents recur across user queries. Thus, fully recomputing documents for every RAG query does redundant compute and increases TTFT. Prior works precompute KV tensors of RAG documents offline and coarsely recompute some tokens during online prefill. However, such KV reuse is often slower than full recomputation on modern GPUs due to high-latency disk transfers. Further, such a coarse-grained recomputation degrades accuracy. To address these limitations, this paper proposes SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance. SIFT processes documents offline and extracts fine-grained locations of high attention scores for each document. Next, we identify the following attention invariance insights that enable us to exploit the extracted locations during runtime: (1) Local-Attention Invariance: The location of high attention scores within a document remain invariant to surrounding documents. This helps us predict the location of high scores where the document attends to itself. (2) Cross-Attention Consistency: Keys with high intra-document attention also attract cross-attention from subsequent documents. This helps us predict the location of high scores where the document attends to future documents. Critically, SIFT stores no KV data and only stores locations of high scores in the form of two compact bit vectors. SIFT's storage is up to 24,000x smaller than KV tensors, obviating costly disk transfers. During prefill, SIFT computes the attention only for the marked locations and improves TTFT by 1.71x while holding accuracy within 1% of full recompute.

Rya Sanovar, Srikant Bharadwaj, Hritvik Taneja +1

Georgia Institute of Technology Atlanta, GA, USA · Microsoft Redmond, WA, USA

Retrieval-Augmented Generation LLM Inference Acceleration Sparse Attention

Jun 8, 2026cs.LG

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose Lookahead Sparse Attention (LSA), a novel inference paradigm powered by a Neural Memory Indexer built upon the DeepSeek-V4 architecture. Rather than passively attending to all historical tokens, LSA proactively predicts future context demands and preserves only the query-critical KV chunks in the GPU memory. Crucially, we instantiate this architecture via a backbone-free decoupled training strategy. By formulating the indexer as a standard dual-encoder architecture, we train it independently using standard retrieval training frameworks without ever loading the massive backbone model into GPU memory. We demonstrate that this "less is more" paradigm significantly maximizes serving efficiency while acting as an effective attention denoiser in tasks that rely on long-term global memory. Across primary long-context evaluation suites (e.g., LongBench-v2, LongMemEval, and RULER), FM-DS-V4 compresses the average physical KV cache footprint down to merely 13.5% of the full-context baseline, while consistently preserving or slightly elevating downstream accuracy (+0.6% absolute margin on average). Crucially, at extreme 500K scales, FlashMemory suppresses the physical KV cache overhead by over 90% without destabilizing the backbone's core reasoning capacities.

Yan Wang, Qifan Zhang, Jiachen Yu +12

Independent Researchers · Tencent · The Hong Kong University of Science and Technology (Guangzhou) +1

KV Caching Long-Context Language Model Inference Memory-Efficient Inference Sparse Attention KV-Cache Compression

Jun 7, 2026cs.CV

Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs

Multimodal Large Language Models (MLLMs) face a significant inference bottleneck due to the quadratic computational cost of self-attention over long visual token sequences. However, we identify a critical inefficiency in current architectures: Visual Attention Saturation. Our analysis reveals that visual tokens rapidly establish their spatial structure and intra-modal relationships in early layers, rendering visual-to-visual self-attention in deeper layers computationally redundant. Conversely, Feed-Forward Networks (FFNs) in these layers remain essential for projecting visual features into the evolving textual semantic space. Leveraging this insight, we present Visual-Skip (V-Skip), a training-free inference paradigm that decouples spatial interaction from semantic evolution. Rather than discarding tokens, V-Skip imposes block-wise structured sparsity by selectively bypassing saturated visual self-attention modules. Furthermore, recognizing that varying downstream tasks demand distinct reasoning depths, V-Skip employs a lightweight, few-shot calibration to dynamically route the task-optimal sparsity path. Extensive experiments demonstrate that V-Skip effectively bypasses redundant vision attention to achieve block-wise sparsity, maintaining a 94.16% to 100.31% performance retention across diverse MLLMs. Ultimately, we prove that to reason more effectively, models do not need to discard what they see -- they simply need to "look less" at the right depth.

Jie Ma, Zhike Qiu, Jiayi Ji +2

Xiamen University

Efficient Multimodal Inference Multimodal Large Language Models Efficient Attention Sparse Attention

Jun 7, 2026cs.LG

Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models

Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive. Since RLVR per-step cost is dominated by long-context rollout generation, sparse attention offers a promising way to accelerate dense rollout. However, sparse rollouts require a delicate stability-efficiency tradeoff: overly aggressive sparsity causes collapse, while overly lenient sparsity gives insufficient speedup. In this work, we study this tradeoff through sparse-to-dense actor-policy mismatch. We first observe that sparse rollout collapse is not driven by uniform degradation across tokens: most sparse tokens align perfectly with dense even under aggressive sparsity. Motivated by this, we hypothesize that sparse rollout training remains stable if the lower tail of per-token actor-policy mismatch stays above a critical threshold throughout the trajectory. We introduce a dynamic sparsity schedule that keeps this tail statistic constant during generation and validate our hypothesis. Across Qwen3 thinking-family models, keeping the tail mismatch statistic near a consistent threshold generally enables stable training. We then use a cost model to find the sparsity schedule for maximum speedup under this mismatch threshold, achieving 2.2x, 2.4x, and 2.0x rollout speedups when training Qwen3-1.7B, Qwen3-4B, and Qwen3-8B. Empirically, we show the thresholds generalize to a larger model (Qwen3-14B) and another RL domain (coding). Finally, our analysis naturally motivates DistillSparse: lightweight LoRA-based distillation on sparse rollout lets more aggressive sparsity reach the same sparse-to-dense mismatch threshold, yielding higher speedup.

Yang Zhou, Ranajoy Sadhukhan, Zhaofeng Sun +7

Carnegie Mellon University · Cornell University · Intel +1

RL for Language Model Reasoning Sparse Attention Reinforcement Learning with Verifiable Rewards

Jun 5, 2026cs.LG

How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models

Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear, or recurrent components. We study how much dense attention is needed to preserve task-level behavior under explicit support granularity and top-k budgets. We introduce an attention-mass top-k oracle for existing GQA checkpoints: for each layer and query position, it computes dense attention, selects head-averaged token support, and recomputes attention only on that support. The oracle is a diagnostic reference, not a deployable accelerator, and separates sparse-budget feasibility from indexer error and runtime realization effects. On Qwen-family retrieval-heavy evaluations, the longest per-query oracle rows stay within 1 point of dense, and a Qwen3.5-9B RULER-style sweep from 4K to 100K stays within 0.48 points. Guided by the oracle, we derive a head-collapsed auxiliary indexer trained by KL distillation from dense attention-mass distributions while keeping the backbone frozen. With separately distilled Qwen3.5-0.8B and Qwen3.5-9B indexers, the reported 16K/32K validation macro gaps are +2.04 and +1.13 points, treated as quality preservation rather than improvement; fused selection-block-shared support can introduce a larger realization gap. Preliminary single-card TTFT measurements show distilled-indexer sparse serving speedups of 1.71x for Qwen3.5-0.8B on NPU and 1.93x for Qwen3.5-9B on GPU against its dense FlashAttention-2 baseline. Additional random-init stress rows reach 3.44x, indicating sparse-runtime headroom but not validated output quality. This first release separates oracle feasibility, distilled-indexer quality, and runtime headroom, leaving a fully matched quality-latency frontier to future work.

Hongxing Wang, Harenome Razanajato, Zhen Zhang +2

Grouped-Query Attention Long-Context Language Modeling LLM Inference Acceleration Efficient Attention Sparse Attention Multi-Head Attention

Jun 4, 2026cs.CL

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought. Existing sparse attention methods often face a practical efficiency-quality trade-off. Structured block sparse methods typically provide stronger acceleration but incur noticeable quality loss, while token sparse methods are usually more accurate yet deliver limited end-to-end speedup because top-k routing over the full cache remains expensive. In this work, we propose cross-layer sparse attention (CLSA), which is built on top of KV-sharing architectures such as YOCO. The core idea is to share not only the KV cache across cross-decoder layers, but also the routing index. A single indexer computes token-level top-k selection once and reuses the resulting index across layers, thereby preserving the fine-grained selectivity of token sparse attention while amortizing the routing overhead. The resulting architecture improves all major inference bottlenecks jointly, including pre-filling, KV-cache storage, and long-context decoding. Experiments across short-context and long-context benchmarks show that CLSA is both accurate and efficient, achieving up to 7.6x decoding speedup and 17.1x overall throughput improvement at 128K context. These results suggest a more complete architectural solution for long-context LLMs that jointly advances model quality and inference efficiency.

Yutao Sun, Yanqi Zhang, Li Dong +2

Microsoft Research · Tsinghua University

Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration Sparse Attention

Jun 4, 2026cs.AI

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents

Sparse attention is becoming increasingly important for serving large language models (LLMs) as generation lengths continue to grow. However, deploying and evaluating new sparse attention algorithms at scale remains highly engineering-intensive, slowing both human researchers and AI agents in exploring the sparse attention design. To address this challenge, we present Vortex, a system that combines a Python-embedded frontend language atop a page-centric tensor abstraction for expressing a broad range of sparse attention algorithms, with an efficient backend tightly integrated into modern LLM serving stacks. Vortex enables rapid prototyping, deployment, and evaluation of sparse attention algorithms, effectively translating their theoretical efficiency gains into real-world throughput improvements. As a result, Vortex substantially accelerates the design and iteration of sparse attention algorithms. First, AI agents use Vortex to automatically generate and refine diverse algorithms, the best reaching up to

3.46\times

higher throughput than full attention while preserving accuracy. Second, Vortex extends sparse attention to emerging architectures and very large models that are otherwise hard to experiment with, reaching up to

4.7\times

higher throughput on the MLA-based GLM-4.7-Flash and

1.37\times

on the 229B-parameter MiniMax-M2.7 on NVIDIA B200 GPUs.

Zhuoming Chen, Xinrui Zhong, Qilong Feng +5

1Carnegie Mellon University · 2Rice University · 3National University of Singapore

LLM Serving LLM Inference Acceleration Sparse Attention

Jun 3, 2026cs.CL

SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

Sparse attention reduces compute and memory bandwidth for long-context LLM inference. However, two key challenges remain: (1) KV cache capacity still grows with sequence length, and offloading to CPU memory introduces a PCIe transfer bottleneck; (2) the sparse selection step itself retains

O(T^2)

complexity and can dominate attention cost at long contexts. We propose SparDA, a decoupled sparse attention architecture that introduces a fourth per-layer projection, the Forecast, alongside Query, Key, and Value. The Forecast predicts the KV blocks needed by the next layer, enabling lookahead selection that overlaps CPU-to-GPU prefetch with current-layer execution. Because Forecast is decoupled from the attention query, our GQA implementation uses one Forecast head per GQA group, reducing selection overhead versus the original multi-head selector. SparDA adds

<

0.5% parameters and trains only the Forecast projections by matching the original selector's attention distribution. On two sparse-pretrained 8B models, SparDA matches or slightly improves accuracy and delivers up to 1.25

\times

prefill speedup and 1.7

\times

decode speedup over the sparse-attention offload baseline. By enabling larger feasible batch sizes on a single GPU, SparDA further reaches up to 5.3

\times

higher decode throughput than the non-offload sparse baseline. Our source code is available at https://github.com/NVlabs/SparDA.

Yaosheng Fu, Guangxuan Xiao, Xin Dong +2

1NVIDIA · 2Thinking Machines Lab · 3ByteDance Seed +1

KV-Cache Offloading Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention

May 31, 2026cs.DC

Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics

Frontier LLMs increasingly decide what a query attends to with a sparse-attention indexer that picks a few KV-cache blocks per query: attention's unit is now a small, reusable chunk. Agentic workloads hammer it: many sub-agents query one large codebase, reusing the same blocks. When that corpus outgrows one GPU it is partitioned across instances, so a query and the blocks it selects often sit on different GPUs: answering it means attention across instances. The reflex of prior cross-instance KV systems is to move the cache: pull the selected blocks to the requester. Multi-head Latent Attention inverts the arithmetic, compressing each token's key and value into one narrow vector, so a routed query row is only ~1 KB, smaller than the chunk it attends; routing the query is then often cheaper than moving the cache. Which primitive wins, over which fabric and request shape, is uncharted, least of all on device-initiated RDMA that makes per-request cross-node transfers cheap. We characterize cross-instance MLA attention on a real multi-node H100 cluster, distilling two reusable artifacts: a topology-aware cost model (probe / transfer / compute / return / merge) and a closed-form route/fetch/local predicate, whose constants we measure on real IBGDA, where the model tracks batched round-trips to within ~7%. At decode it routes the query, trading the cost of moving the cache (a ~3 ms re-adaptation splice for a contiguous chunk, or a scattered gather under selection) for a tens-of-microsecond round trip, and picks the fabric by probe latency, not peak bandwidth. We instantiate the cost model and predicate for MLA, but neither is MLA-specific: they apply wherever compression or sparse selection shrinks attention to small chunks (DeepSeek-V3.2, V4, and GLM-5.1 today). Extending them to a new architecture requires measuring just two coefficients: the routed payload and fetch's move-the-cache cost.

Bole Ma, Jan Eitzinger, Harald Köstler +1

LLM Inference KV Caching Sparse Attention Attention Mechanisms Distributed Inference Multi-Head Latent Attention

May 29, 2026cs.CV

LVSA: Training-Free Sparse Attention for Long Video Diffusion

Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and beyond the training horizon the model converges to near-static output, that is, "frozen" repetitive video. State of the art approaches are either too costly, e.g., they require retraining, or fail to satisfy both performance and quality objectives in a scalable manner. To this end, we introduce Long Video Sparse Attention (LVSA), a training-free model-agnostic block-sparse attention for video diffusion transformers that combines a structured window pattern with rotating global anchors, thus removing the fixed-grid bias which causes long-range temporal artifacts. LVSA, combined with a FlashInfer kernel, reduces compute up to 3.17x on Wan 2.1 1.3B at a 6x horizon, 2.98x on Wan 2.1 14B at a 6x horizon, and 3.33x on HunyuanVideo 1.5 at a 1.5x horizon, compared to dense attention. Beyond reducing compute, LVSA enables HunyuanVideo 1.5 generation at a 2x horizon, which is otherwise out-of-memory on a single GPU. Moreover, LVSA provides speedups up to 2.41x compared to RIFLEx and 3.27x compared to UltraViCo on Wan 2.1 1.3B. To demonstrate applicability across diverse platforms, we apply LVSA on NPUs and achieve speedups up to 2.71x on Wan 2.2 A14B and 3.24x on Wan 2.1 1.3B compared to dense attention. To evaluate quality in a fair way, we introduce VQeval, a tool properly scoring loopy video failures, which instead are rewarded in state of the art evaluators like VBench-Long. LVSA is quality-neutral for generation at training horizon length and quality-positive at extended lengths.

Gael Glorian, Ioannis Lamprou, Zhen Zhang +2

Distributed Parallel Technology Laboratory, Paris Research Center, Huawei Technologies France · AI Framework and Data Technology Lab, Huawei Technologies Co., Ltd.

Video Diffusion Models Long-Horizon Video Generation Sparse Attention Diffusion Model Inference Acceleration Temporal Consistency in Video Generation Block-Sparse Attention

May 28, 2026cs.CV

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation

Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a growing historical KV cache. Existing methods reduce this cost by truncating the KV cache or compressing it into implicit memory, but both lose explicit access to query-relevant historical details. We propose OmniMem, an explicit full-range memory retrieval framework that performs sparse KV retrieval over the historical cache. To make this practical for chunk-based AR video generation, OmniMem addresses two issues: (i) local bias in sparse KV selection and (ii) Union Explosion in memory access. Adaptive Window Exclusion removes local-window blocks from the selection candidates when sufficient long-range history is available, preserving the sparse budget for informative long-range retrieval. Query-Shared KV Selection reduces cross-query diversity, while Per-Head Scattered KV Access avoids expanding head-specific selections into a large selected KV buffer. This allows each attention head to retrieve non-contiguous KV blocks according to its own selection pattern. Experiments on long-video generation show that OmniMem improves Dynamic Degree by 52.3% and preserves strong consistency over strong baselines, while maintaining comparable memory usage.

Lin Zhao, Yushu Wu, Yifan Gong +2

Northeastern University · Adobe Research

KV Caching Long Video Generation Memory-Augmented Video Generation Sparse Attention Autoregressive Video Generation Temporal Consistency in Video Generation