一作ACL 2026Findings· Findings of ACL
POP : Prefill-Only Pruning for Efficient Large Model Inference
Junhui He · Zhihui Fu · Jun Wang · Qingan Li
摘要
Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities.However, their deployment is hindered by significant computational costs. Existing structured pruning methods, while hardware-efficient, often suffer from significant accuracy degradation. In...