3 papers
cs.IR2022
Learning to Collide: Recommendation System Model Compression with Learned Hash Functions
Benjamin Ghaemmaghami, Mustafa Ozdal, Rakesh Komuravelli +4
A key characteristic of deep recommendation models is the immense memory requirements of their embedding tables. These embedding tables can often reach hundreds of gigabytes which…
cs.AR2021
Supporting Massive DLRM Inference Through Software Defined Memory
Ehsan K. Ardestani, Changkyu Kim, Seung Jae Lee +17
Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1.5x per year. With model size soon to be in tera…
cs.DC2020
Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems
Maxim Naumov, John Kim, Dheevatsa Mudigere +12
Large-scale training is important to ensure high performance and accuracy of machine-learning models. At Facebook we use many different models, including computer vision, video and…