← all papers · overview

Diffkv: Differentiated Memory Management For Large Language Models With Parallel KV Compaction

Abstract

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression techniques, such as quantization and pruning, apply uniform treatment to both keys and values, and discard unimportant tokens entirely, overlooking the fine-grained disti

Related papers

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