Deep learning recommendation models (DLRMs) have been used across many business-
critical services at Meta and are the single largest AI application in terms of infrastructure …

Personalized recommendation systems are gaining significant traction due to their industrial
importance. An important building block of recommendation systems consists of the …

The advent of AI has driven the adoption of high density low precision arithmetic on FPGAs.
This has resulted in new methods in mapping both arithmetic functions as well as dataflows …

Deep learning based recommendation systems form the backbone of most personalized
cloud services. Though the computer architecture community has recently started to take …

Online inference is becoming a key service product for many businesses, deployed in cloud
platforms to meet customer demands. Despite their revenue-generation capability, these …

Recommendation models rely on deep learning networks and large embedding tables,
resulting in computationally and memory-intensive processes. These models are typically …

Deep learning model inference is a key service in many businesses and scientific discovery
processes. This paper introduces Ribbon, a novel deep learning inference serving system …

During the past decade, novel Deep Learning (DL) algorithms/workloads and hardware
have been developed to tackle a wide range of problems. Despite the advances in …

The memory-intensive embedding layers of the personalized recommendation systems are
the performance bottleneck as they demand large memory bandwidth and exhibit irregular …

Embedding tables dominate industrial-scale recommendation model sizes, using up to
terabytes of memory. A popular and the largest publicly available machine learning MLPerf …