"Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via ..."

Fangcheng Liu et al. (2024)

> Home

Details and statistics

DOI: —

access: closed

type: Conference or Workshop Paper

metadata version: 2025-02-05

- view
  - electronic edition @ nips.cc
- export record
  dblp key:
  - conf/nips/LiuT0NT0024
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/nips/LiuT0NT0024
Fangcheng Liu, Yehui Tang, Zhenhua Liu, Yunsheng Ni, Duyu Tang, Kai Han, Yunhe Wang:
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting. NeurIPS 2024

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.