Litcius/Paper detail

POD-A <scp>ttention</scp> : Unlocking Full Prefill-Decode Overlap for Faster LLM Inference

Aditya K. Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar

202511 citationsDOIOpen Access PDF

Topics & Concepts

InferenceComputer sciencePoint of deliveryComputer networkArtificial intelligenceBiologyAgronomyNatural Language Processing TechniquesTopic Modeling
POD-A <scp>ttention</scp> : Unlocking Full Prefill-Decode Overlap for Faster LLM Inference | Litcius