arXiv:2609.37261v1 Announce Type: new Abstract: Softmax attention is ubiquitous in modern machine learning, but its quadratic scaling with sequence length makes it costly. To reduce this cost, attent...
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:2605. 16928v2 Announce Type: replace-cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention.
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: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.
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.
arXiv:2608. 06849v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs.
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.
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:2601. 03043v4 Announce Type: replace-cross Abstract: Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency.
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.
arXiv:2609. 31093v1 Announce Type: new Abstract: Scaling language models to long contexts is limited by the quadratic cost of self-attention.