2025
Squeezed Attention: Accelerating Long Context Length LLM Inference
Coleman Richard Charles Hooper, Sehoon Kim, Hiva Mohammadzadeh, Monishwaran Maheswaran, Sebastian Zhao, June Paik +3
ACL 2025long
Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation.For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the…