The use of GPUs has proliferated for machine learning workflows and is now considered
mainstream for many deep learning models. Meanwhile, when training state-of-the-art …

We propose RecShard, a fine-grained embedding table (EMB) partitioning and placement
technique for deep learning recommendation models (DLRMs). RecShard is designed …

Checkpoints play an important role in training long running machine learning (ML) models.
Checkpoints take a snapshot of an ML model and store it in a non-volatile memory so that …

Deep Learning Recommendation Models (DLRMs) are very popular in personalized
recommendation systems and are a major contributor to the data-center AI cycles. Due to the …

To meet the strict service level agreement requirements of recommendation systems, the
entire set of embeddings in recommendation systems needs to be loaded into the memory …

Deep learning recommendation systems must provide high quality, personalized content
under strict tail-latency targets and high system loads. This paper presents RecPipe, a …

Deep learning recommendation models have grown to the terabyte scale. Traditional
serving schemes-that load entire models to a single server-are unable to support this scale …

We present FleetRec, a high-performance and scalable recommendation inference system
within tight latency constraints. FleetRec takes advantage of heterogeneous hardware …

Personalized recommendation is an important class of deep-learning applications that
powers a large collection of internet services and consumes a considerable amount of …

Deep learning recommendation systems serve personalized content under diverse tail-
latency targets and input-query loads. In order to do so, state-of-the-art recommendation …