ResearchTrend.AI
SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

Jinwoo Park
Seunggeun Cho
Dongsu Han
ArXiv (abs)PDFHTML

Papers citing "SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs"

2 / 2 papers shown
Title
PEARL: Parallel Speculative Decoding with Adaptive Draft Length
PEARL: Parallel Speculative Decoding with Adaptive Draft Length
Tianyu Liu
Yun Li
Qitan Lv
Kai Liu
Jianchen Zhu
Winston Hu
Xingwu Sun
138
20
0
13 Aug 2024
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Yuhui Li
Fangyun Wei
Chao Zhang
Hongyang R. Zhang
150
165
0
26 Jan 2024