conftrace_

tokenwise quantization

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

normalized attention score (1) large language model (1) attention score (1) salient token identification (1) adaptive compression (1) kv cache quantization (1) flash attention (1) attention mechanism (1) model compression (1)

Papers

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification NeurIPS 2024