Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2509.18344
Cited By
v1
v2 (latest)
Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
22 September 2025
Pei-Shuo Wang
Jian-Jia Chen
Chun-Che Yang
Chi-chih Chang
N. Huang
Mohamed S. Abdelfattah
Kai-Chiang Wu
MQ
Re-assign community
ArXiv (abs)
PDF
HTML
Github (5★)
Papers citing
"Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding"
0 / 0 papers shown
No papers found
Page 1 of 0
