AI News HubLIVE
原文2 min read

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

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.

SourcearXiv Computational LinguisticsAuthor: Chen Qiu, Guozhong Li, Panos Kalnis

[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?)