This post describes the next generation of Meta Andromeda, Meta’s personalized ads retrieval engine, and how co-designing the model, system, and GPU hardware unlocks a new efficiency frontier for ads retrieval. In production, the system scores every eligible ad with near ranking-level model performance at retrieval scale and surfaces the top candidates at over one [...]
The post Meta Andromeda: Powering the Next Generation of Ads Retrieval Through Model-System Co-Design appeared first on Engineering at Meta.
source & further reading
engineering.fb.com — original article
Evaluating voice agent quality at scale
Improving caller identification for voice AI agents
A simple fix for LLM tail latency