chengluo's picture

2 1

chengluo

wdlctc

·

AI & ML interests

None yet

Recent Activity

authored a paper 5 days ago

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

upvoted a paper 5 days ago

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

commented on a paper 5 days ago

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

View all activity

Organizations

None yet

Papers 2

arxiv:2502.12574

arxiv:2407.15892

models

None public yet

datasets

None public yet