作者位次 #6/8FAST 2026Oral· Storage & File Systems
Accelerating Model Loading in LLM Inference by Programmable Page Cache
Yubo Liu · Hongbo Li · Xiaojia Huang · Yongfeng Wang · Hanjun Guo · Hui Chen · Yuxin Ren · Ning Jia
摘要
This paper examines the model loading bottleneck during the LLM inference startup. Existing solutions often optimize model loading performance at the expense of compatibility. However, compatibility is a crucial factor determining whether a technology can be widely applied in real-world scenarios...