"DeFT: Flash Tree-attention with IO-Awareness for Efficient ..."

Jinwei Yao et al. (2024)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2404.00242

access: open

type: Informal or Other Publication

metadata version: 2024-05-08

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2404-00242
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2404-00242
Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, Tao Lin:
DeFT: Flash Tree-attention with IO-Awareness for Efficient Tree-search-based LLM Inference. CoRR abs/2404.00242 (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.