ART: Attention Run-time Termination for Efficient Large Language Model Decoding

• URL: http://arxiv.org/abs/2606.00024v2
• Date: Mon, 08 Jun 2026 13:51:37 GMT
• Title: ART: Attention Run-time Termination for Efficient Large Language Model Decoding
• Abstract summary: Long-context decoding in Large Language Models (LLMs) is constrained by the cost of accessing and processing the Key-Value ( KV) cache.<n>We propose Attention Run-time Termination (ART), a lightweight run-time mechanism that tracks accumulated attention outputs during kernel execution.<n>Experiments on LongBench and RULER Needle-in-a-Haystack tasks show that ART increases the generation throughput of existing KV-cache methods by up to 20%.
• Score: 7.365525319097287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-context decoding in Large Language Models (LLMs) is constrained by the cost of accessing and processing the Key-Value (KV) cache. Despite the evidence that attention outputs depend jointly on keys and values, most existing KV management methods rely on key-only pruning, as incorporating values incurs prohibitive additional overhead. In this paper, we propose Attention Run-time Termination (ART), a lightweight run-time mechanism that tracks accumulated attention outputs during kernel execution and terminates subsequent KV block accesses once further contributions become negligible. Rather than replacing KV selection, ART dynamically terminates redundant KV traversal on top of existing dense or sparse attention policies. We introduce a stability-based criterion that monitors both magnitude and directional changes of intermediate attention outputs, and provide a theoretical characterization of the resulting truncation error. Experiments on LongBench and RULER Needle-in-a-Haystack tasks show that ART increases the generation throughput of existing KV-cache methods by up to 20%, without compromising the quality of the results.

Related papers

• CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration [67.17709877327232]
  Cate KV is a hybrid KV cache method that retains only critical token information for consistent heads.<n>Cate KV reduces memory usage by up to $2.72times$ and accelerates decoding by $2.18times$ in single-sample inputs.
  arXiv  Detail & Related papers  (2026-08-31T06:02:37Z)
• ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing [41.23077900713446]
  Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches.<n>We propose ReST-KV, a robust KV eviction method that combines layer-wise output Reconstruction and Spatial-Temporal smoothing.
  arXiv  Detail & Related papers  (2026-05-09T09:49:32Z)
• DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity [50.52392445266824]
  We propose a residual-based KV cache compression framework motivated by long-range inter-token similarity and highly shared latent components in KV representations.<n>Instead of discarding tokens, DeltaKV encodes semantic residuals relative to retrieved historical references, preserving fidelity while substantially reducing storage.<n>Experiments show that DeltaKV reduces KV cache memory to 29% of the original while maintaining near-lossless accuracy on LongBench, SCBench, and AIME.
  arXiv  Detail & Related papers  (2026-02-08T15:14:36Z)
• ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution [84.41751286055909]
  We develop a training-based KV cache eviction framework that learns to predict which KV pairs to evict during longtext generations.<n>We formulate cache eviction as a Markov Decision Process and apply the GRPO algorithm to mitigate the significant language modeling loss increase on low-entropy tokens.
  arXiv  Detail & Related papers  (2026-02-03T07:16:51Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• G-KV: Decoding-Time KV Cache Eviction with Global Attention [57.47409249054187]
  Large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths.<n> KV cache compression has emerged as an effective approach to greatly enhance the efficiency of reasoning.<n>We propose G-KV, a KV cache eviction method that employs a global scoring mechanism, combining local and historical attention scores to more accurately assess token importance.
  arXiv  Detail & Related papers  (2025-11-29T14:21:33Z)
• LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences [12.093166735658626]
  Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models.<n>It introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios.<n>Existing KV retrieval methods suffer from notable efficiency and accuracy bottlenecks due to per-token retrieval and coarse-grained page-level KV management.
  arXiv  Detail & Related papers  (2025-10-13T11:28:30Z)
• Value-Guided KV Compression for LLMs via Approximated CUR Decomposition [24.262712463465665]
  CurDKV is a novel, value-centric KV compression method that selects keys and values based on leverage scores computed from CUR matrix decomposition.<n>Our approach approximates the dominant subspace of the attention output $softmax(QKT)V$, ensuring that the retained tokens best preserve the model's predictive behavior.
  arXiv  Detail & Related papers  (2025-09-18T15:04:06Z)
• Retrospective Sparse Attention for Efficient Long-Context Generation [5.562294018150909]
  RetroAttention retrospectively revises past attention outputs using newly arrived KV entries from subsequent decoding steps.<n>This breaks the fixed-attention-output paradigm and allows continual correction of prior approximations.<n>Experiments show that RetroAttention consistently outperforms state-of-the-art (SOTA) KV compression methods.
  arXiv  Detail & Related papers  (2025-08-12T15:11:47Z)
• KeepKV: Eliminating Output Perturbation in KV Cache Compression for Efficient LLMs Inference [16.53643930310808]
  KeepKV is a novel adaptive KV cache merging method designed to eliminate output perturbation while preserving performance under strict memory constraints.<n>We show that KeepKV substantially reduces memory usage, enhances inference throughput by more than 2x and keeps superior generation quality even with 10% KV cache budgets.
  arXiv  Detail & Related papers  (2025-04-14T06:58:00Z)
• DBudgetKV: Dynamic Budget in KV Cache Compression for Ensuring Optimal Performance [125.81664663201282]
  We introduce a new KV cache compression method dubbed DBudgetKV.<n>It features an attention-based metric to signal when the remaining KV cache is unlikely to match the full-cache performance.<n>Our method achieves lossless KV pruning effectively and robustly, exceeding 25% compression ratio on average.
  arXiv  Detail & Related papers  (2025-02-24T06:33:39Z)
• More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression [71.42818367729573]
  In large language models (LLMs), the memory usage of KV cache has become a critical bottleneck during inference.<n>The mainstream KV compression methods, including KV pruning and KV quantization, primarily focus on either token or precision dimension separately.<n>In this paper, we comprehensively investigate the token-precision trade-off in KV cache compression.
  arXiv  Detail & Related papers  (2024-12-17T09:20:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.