1
ReFreeKV: Towards Threshold-Free KV Cache Compression
新论文提出ReFreeKV，无需预设阈值的KV缓存压缩，实现无损内存缩减，解决现有方法依赖人工设定预算的痛点。
arXiv:2502.16886v4 Announce Type: replace-cross Abstract: To reduce memory consumption during LLM inference, a handful of methods have been proposed f…