paper-with-me

홈 › Papers

G-KV: Decoding-Time KV Cache Eviction with Global Attention

2025-11-29 · Mengqi Liao, Lu Wang, Chaoyun Zhang, Zekai Shen, Xiaowei Mao, Si Qin, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Huaiyu Wan arxiv

Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compression has emerged as an effective approach to greatly enhance the efficiency of reasoning. However, existing methods often focus on prompt compression or token eviction with local attention score, overlooking the long-term importance of tokens. 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. Additionally, we introduce post-training techniques, including reinforcement learning and distillation, to optimize models for compressed KV cache settings. The code of this paper is available on: https://github.com/microsoft/G-KV.

📄 PDF Abstract BibTeX arXiv:2512.00504

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction

2025-09-13 · Yijun Liu, Yixuan Wang, Yuzhuang Xu, Shiyu Ji 외 arxiv

Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the sequence extends, which seriously affects mem…

Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models

2026-02-02 · Xindian Ma, Yidi Lu, Peng Zhang, Jing Zhang arxiv

The integration of visual information into Large Language Models (LLMs) has enabled Multimodal LLMs (MLLMs), but the quadratic memory and computational costs of Transformer architectures remain a bottleneck. Existing KV …

Story Generation

RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction

2026-04-14 · Sihao Liu, YuFan Xiong, Zhonghua Jiang, Zhaode Wang 외 arxiv

Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the visual KV cache when processing long visual contexts. Existing KV cache c…

Computational Efficiency

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query

2025-05-24 · YiXuan Wang, Shiyu Ji, Yijun Liu, Yuzhuang Xu 외

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challen…

Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction

2025-08-04 · Yuerong Song, Xiaoran Liu, Ruixiao Li, Zhigeng Liu 외 arxiv

Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniq…