• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Efficient Prompt Caching via Embedding Similarity.

Hanlin ZhuBanghua ZhuJiantao Jiao
Published in: CoRR (2024)
Keyphrases
  • similarity measure
  • query processing
  • neural network
  • computationally expensive
  • prefetching
  • image segmentation
  • similarity metric
  • genetic algorithm
  • database systems
  • cost effective
  • data access