Cite
Notes
Only stored in your browser.
Attribution
Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
arXiv 2025
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
arXiv 2024
from 2 papers
Lijie Yang
Ravi Netravali
Rui Pan
Zhihao Jia
Zhihao Zhang
Zikun Li