paper-with-me

Papers

Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques

2025-03-14 · Neusha Javidnia, Bita Darvish Rouhani, Farinaz Koushanfar

Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens, presenting significant efficiency challenges. This paper presents an analysis of various Key-Value (KV) cache compression strategies, offering a comprehensive taxonomy that categorizes these methods by their underlying principles and implementation techniques. Furthermore, we evaluate their impact on performance and inference latency, providing critical insights into their effectiveness. Our findings highlight the trade-offs involved in KV cache compression and its influence on handling long-context scenarios, paving the way for more efficient LLM implementations.

📄 PDF Abstract BibTeX arXiv:2503.11816

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference

2025-05-28 · Donghyeon Joo, Helya Hosseini, Ramyad Hadidi, Bahar Asgari

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic explorati…

CodeComp: Structural KV Cache Compression for Agentic Coding

2026-04-11 · Qiujiang Chen, Jing Xiong, Chenyang Zhao, Sidi Yang 외 arxiv

Agentic code tasks such as fault localization and patch generation require processing long codebases under tight memory constraints, where the Key-Value (KV) cache becomes the primary inference bottleneck. Existing compr…

Code Generation

The risk of KV cache compression

2026-07-01 · Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno, Sebastian Trimpe 외 arxiv

Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compression, which replaces the full cache with…

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

2026-09-04 · Janghyeon Kim, Minsoo Kim, Kyuhong Shim, Jungwook Choi arxiv

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bott…

Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving

2025-03-31 · Wei Gao, Xinyu Zhou, Peng Sun, Tianwei Zhang 외

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to…

Computational EfficiencyLanguage ModelingLanguage ModellingLarge Language Model