Cite
Notes
Only stored in your browser.
Attribution
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
arXiv 2025
from 1 papers
Hoyun Song
Huije Lee
Jeongyeon Seo
Jong C. Park
Sangjin Choi
Soyeong Jeong
Sukmin Cho
Taeho Hwang