3 papers
cs.CL2026
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
Junhao Hu, Fangze Li, Mingtao Xu +9
Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference e…
cs.LG2026
You Need an Encoder for Native Position-Independent Caching
Shiju Zhao, Junhao Hu, Jiaqi Zheng +1
The Key-Value (KV) cache of Large Language Models (LLMs) is prefix-based, making it highly inefficient for processing contexts retrieved in arbitrary order. Position-Independent Ca…
cs.LG2025
MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving
Shiju Zhao, Junhao Hu, Rongxiao Huang +2
The context caching technique is employed to accelerate the Multimodal Large Language Model (MLLM) inference by prevailing serving platforms currently. However, this approach merel…