HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
Paper
•
2502.12574
•
Published
•
10
Jinqi Xiao
jinqixiao
AI & ML interests
None yet
Recent Activity
authored
a paper
7 days ago
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
authored
a paper
over 1 year ago
COMCAT: Towards Efficient Compression and Customization of
Attention-Based Vision Models
upvoted
a
paper
over 1 year ago
COMCAT: Towards Efficient Compression and Customization of
Attention-Based Vision Models
Organizations
None yet
jinqixiao's activity
authored
a
paper
7 days ago
authored
a
paper
over 1 year ago