4 papers
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…
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
Junhao Hu, Wenrui Huang, Weidong Wang +6
Large Language Models (LLMs) have demonstrated strong capabilities across various domains, with recent advancements in challenging reasoning tasks such as mathematics and programmi…
Modified Wave operators for the Hartree equation with repulsive Coulomb potential
Wenrui Huang
We study the final state problem for the Hartree equation with repulsive Coulomb potential: \[i\partial_t u+\frac{1}{2}Δu-\frac{1}{|x|}u=((-Δ)^{-1}|u|)^2u\] We show the work in \ci…
EPIC: Efficient Position-Independent Caching for Serving Large Language Models
Junhao Hu, Wenrui Huang, Weidong Wang +7
Large Language Models (LLMs) show great capabilities in a wide range of applications, but serving them efficiently becomes increasingly challenging as requests (prompts) become mor…