← all papers · overview

Chunkkv: Semantic-preserving KV Cache Compression For Efficient Long-context LLM Inference

Abstract

Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70% of total memory during inference. Although existing compression methods reduce memory by evaluating the importance of individual tokens, they overlook critical semantic relationships between tokens, resulting in fragmented context and degraded performance. We in

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).