FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation
Paper
•
2502.01068
•
Published
•
17
•
2
Dongwon Jo
dongwonjo
AI & ML interests
Efficient AI, Model Compression, Quantization, Pruning, Generative Model, Large Language Model, Diffusion
Recent Activity
authored
a paper
13 days ago
Reasoning Path Compression: Compressing Generation Trajectories for
Efficient LLM Reasoning
upvoted
a
paper
4 months ago
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for
Large Language Models
Organizations
None yet
dongwonjo's activity
commented
a
paper
4 months ago
commented
a
paper
12 months ago