# Scaling TensorFlow to 300 million predictions per second

arXiv: https://arxiv.org/abs/2109.09541 · HTML: https://mlsanity.com/paper/2109.09541/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 7 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 3 of 3)

- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting](https://mlsanity.com/paper/1610.03013/) (2016)

## Built on by (most cited first, 2 of 2)

- [Exploration with Model Uncertainty at Extreme Scale in Real-Time Bidding](https://mlsanity.com/paper/2208.01951/) (2022)
- [Unleash the Power of Context: Enhancing Large-Scale Recommender Systems with Context-Based Prediction Models](https://mlsanity.com/paper/2308.01231/) (2023)

## Abstract (arXiv)

We present the process of transitioning machine learning models to the TensorFlow framework at a large scale in an online advertising ecosystem. In this talk we address the key challenges we faced and describe how we successfully tackled them; notably, implementing the models in TF and serving them efficiently with low latency using various optimization techniques.