Rongtian Fu, Shigang Li 0002, Youxuan Xu, Tong Wu 0024, Zhi Ma, Jinliang Shi. Omnia: Efficient RAG Serving through Speculative Scheduling. In Sanmukh Kuppannagari, Mehmet Koyutürk, Alfredo Goldman, Dimitrios S. Nikolopoulos, editors, Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2026, Cleveland, OH, USA, July 13-16, 2026. pages 165-178, ACM, 2026. [doi]
Abstract is missing.