1
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
突破性KV缓存量化方案，实现sub-1-bit压缩，大幅降低推理内存开销却不损精度。
arXiv:2607.01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrain…