待翻译：ART: Attention Run-time Termination for Efficient Large Language Model Decoding
AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2606.00024v1 Announce Type: new Abstract: Long-context decoding in Large Language Models (LLMs) is severely constrained by the memory bandwidth required to fetch the extensive Key-Value (KV) cache. Most existing KV management methods rely on key-only pruning before decoding, despite the evidence that attention outputs depend jointly on keys and values, as incorporating values in their methods 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. This design makes ART orthogonal to existing key-based KV cache management methods, enabling seamless integration with them. Experiments on LongBench benchmarks show that ART achieves 20% higher generation throughput in large batch size than state-of-the-art baseline while maintaining comparable accuracy.
AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。
[2606.00024] ART: Attention Run-time Termination for Efficient Large Language Model Decoding [Submitted on 15 Apr 2026] Title:ART: Attention Run-time Termination for Efficient Large Language Model Decoding View a PDF of the paper titled ART: Attention Run-time Termination for Efficient Large Language Model Decoding, by Chen Qiu and Guozhong Li and Panos Kalnis View PDF HTML (experimental) Abstract:Long-context decoding in Large Language Models (LLMs) is severely constrained by the memory bandwidth required to fetch the extensive Key-Value (KV) cache. Most existing KV management methods rely on key-only pruning before decoding, despite the evidence that attention outputs depend jointly on keys and values, as incorporating values in their methods 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. This design makes ART orthogonal to existing key-based KV cache management methods, enabling seamless integration with them. Experiments on LongBench benchmarks show that ART achieves 20% higher generation throughput in large batch size than state-of-the-art baseline while maintaining comparable accuracy. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2606.00024 [cs.CL] (or arXiv:2606.00024v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.00024 arXiv-issued DOI via DataCite Submission history From: Chen Qiu [view email] [v1] Wed, 15 Apr 2026 06:55:14 UTC (732 KB) Full-text links: Access Paper: View a PDF of the paper titled ART: Attention Run-time Termination for Efficient Large Language Model Decoding, by Chen Qiu and Guozhong Li and Panos Kalnis View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)