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.
arXiv:2605. 16928v2 Announce Type: replace-cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention.
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×.
The paper introduces Pre-hoc Sparsity (PrHS), a method that selects key-value (KV) cache entries before attention scoring to avoid posterior bias in large language model inference. By bounding mutual‑information loss through the dropped attention mass, PrHS offers explicit accuracy control and implements three orthogonal selectors across time, depth, and layer. Experiments on LLaMA and Mistral models show that PrHS cuts retrieval overhead by over 90%, achieves higher sparsity than HShare, and delivers significant speedups and reduced FLOPs on NVIDIA A100 GPUs while maintaining near‑dense accuracy.
arXiv:2607. 09052v1 Announce Type: new Abstract: Block sparse attention is a hardware friendly way to alleviate the key-value (KV) cache read bottleneck in large language models (LLMs).
arXiv:2604. 20920v2 Announce Type: replace Abstract: Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components.
Prism Attention introduces a proposal‑refined sparse attention framework that replaces static cross‑layer index reuse with a coarse‑to‑fine strategy, allowing layer‑wise adaptability while maintaining efficiency. The method leverages the observation that high‑attention tokens remain largely stable across layers, with changes concentrated near the boundary of previously selected regions. Experiments demonstrate state‑of‑the‑art performance on reasoning and long‑context benchmarks, achieving a 3.4× decoding speedup over FlashAttention at 128K context length.
arXiv:2609.13141v1 Announce Type: new Abstract: Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context u...
arXiv:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.
arXiv:2508. 18224v3 Announce Type: replace-cross Abstract: Recent advances in sparse attention mechanisms have demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs).
Elastic Threshold Attention (ETA) is a trainable attention mechanism that dynamically predicts contextual thresholds from query representations, enabling selective pruning of KV cache tokens during long‑context decoding. By multiplicatively suppressing sub‑threshold logits during training, ETA avoids representation collapse and eliminates localized attention sinks, allowing a 1.45B model to match dense attention performance at roughly 85% training sparsity and 38% active decode density. At inference, a custom Triton kernel achieves up to 2.5× faster decoding on sequences up to 512K tokens, and an offline calibration step can further reduce compute by 27% by freezing per‑head thresholds.
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.
arXiv:2609.36835v1 Announce Type: new Abstract: Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for...