GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache

By Soosung Kim · Paper · cs.LG

The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache memory. Vector Quantization (VQ), particularly Residual Quantization (RQ), is a promising approach for pushing KV cache storage to

Cs.lg

View original

HomeResourceLoading…