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

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time.

Zichang LiuJue WangTri DaoTianyi ZhouBinhang YuanZhao SongAnshumali ShrivastavaCe ZhangYuandong TianChristopher RéBeidi Chen
Published in: CoRR (2023)
Keyphrases
  • bayesian networks
  • cost effective
  • database
  • databases
  • data mining
  • genetic algorithm
  • computer vision
  • data structure
  • high dimensional
  • lightweight