nzhiltsov

GPU retrieval can rival HNSW/IVFPQ on both latency and recall. LinkedIn's LiNR (Feed OON recsys) and SJS and Meta's MoL already deploy exhaustive k-NN at production scale on A100/H100 nodes. See my full post for the technical details

This is our team’s work on LLM productionization for RecSys from a year ago. Since September 2024, it has powered the most member experience in job recommendations and search at Linkedin. A strong example of thoughtful ML system design, it may be particularly relevant for ML/AI practitioners.