Skip to content
conftrace_

pivot token

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (1) large language model quantization (1) attention score (1) quantization error (1) kv cache (1) attention mechanism (1) model quantization (1) model compression (1)

Papers

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact ACL 2024