Meta explains Intelligent Delivery, its ML system for allocating ad-ranking compute
Overview
Meta says Intelligent Delivery is an ML-driven system that allocates compute across its ads serving stack and has contributed about a 10% ranking performance gain since 2017.
Meta's engineering blog describes its approach: ML models that predict the marginal utility of compute, multi-layered mechanisms that move resources across the system, and agentic AI that detects and responds to system shifts.
The system uses the Resource Core Model, a 6B sparse and 20M dense parameter model that runs before candidate retrieval. Meta says it predicts which ad requests benefit most from additional compute.
Written by AI from the articles below · updated Nov 11, 12:18 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Engineering at MetaOfficialMeta explains how Intelligent Delivery allocates compute for ads ranking
AIMeta says Intelligent Delivery is an ML-driven system that allocates compute across its ads serving stack and has contributed about a 10% ranking performance gain since 2017. The system uses the Resource Core Model, a 6B sparse and 20M dense parameter model that runs before candidate retrieval to predict which ad requests benefit most from additional compute.
Heat Trend
- Current comparable heat
- 6
- Peak comparable heat
- 10Nov 11, 1:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.