AI RESEARCH
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
arXiv CS.CL
•
ArXi:2603.22910v1 Announce Type: new The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank compression methods often rely on irreversible parameter transformations, sacrificing the flexibility to switch back to full-precision inference when memory is abundant. In this paper, we propose EchoKV, a flexible KV cache compression scheme that enables on-demand transitions between standard and compressed inference.