Login / Signup

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression.

Peiyu LiuZe-Feng GaoWayne Xin ZhaoYipeng MaTao WangJi-Rong Wen
Published in: CoRR (2024)
Keyphrases
  • data analysis
  • raw data
  • data sets
  • data points
  • high dimensional
  • query processing
  • small number
  • graph representation