Meta Andromeda retrieval model scores over one billion ads per second
AIMeta's Andromeda ads retrieval system now scores every eligible ad with near ranking-level model performance and surfaces top candidates at over one billion ads per second, a 100x lift over the 2024 system. The new architecture uses LLM-inspired mixture-of-experts and runs at approximately 300x fewer inference-time FLOPs than the 2024 Andromeda retrieval model.
Source details
Engineering at Meta · engineering.fb.comPublished
Original title: Meta Andromeda: Powering the Next Generation of Ads Retrieval Through Model-System Co-Design