Jul 2026
Kalypso: Relational LLM Serving
Kalypso is presented, a relational LLM serving system that exposes an API for semantic query plans and executes them using an adaptive, memory-aware scheduling algorithm, demonstrating that query-aware LLM serving can substantially improve the efficiency of semantic query execution.
Hojae Son, Md Ashraful Islam, H. Cao et al.
· arXiv.org · 0 citations