WindowKV: Task-adaptive group-wise KV cache window selection for efficient LLM inference

Expert Systems with Applications 2026 Open access

Read full text

Authors: Youhui Zuo, Sibo Wei, Chen Zhang, Zhuorui Liu, Wenpeng Lü, Dawei Song

DOI: 10.1016/j.eswa.2026.134291

Cited by: 0

References: 42

Fields of Study & Subjects

Advanced Data Storage Technologies Algorithms and Data Compression Distributed and Parallel Computing Systems

References 42