Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Paper
•
2502.05609
•
Published
•
17
Jeong yeon Seo
yenaa
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
12 days ago
Benchmarking LLMs for Political Science: A United Nations Perspective
upvoted
a
paper
about 2 months ago
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Organizations
None yet