Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time.
Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher R, Beidi Chen
Browse the full ICML paper archive.
Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher R, Beidi Chen
Browse the full ICML paper archive.