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

Knowledge graph reasoning (KGR) answers logical queries over a knowledge graph (KG),
and embedding-based KGR (EKGR) becomes popular recently, which embeds both queries …

Deep Learning Recommendation Models (DLRMs) have gained popularity in
recommendation systems due to their effectiveness in handling large-scale recommendation …

In numerous production environments, Approximate Nearest Neighbor Search (ANNS) plays
an indispensable role, particularly when dealing with massive datasets that can contain …

Training large-scale deep learning recommendation models (DLRMs) with embedding
tables stretching across multiple GPUs in a cluster presents a unique challenge, demanding …

This paper documents our characterization study and practices for serving text-to-image
requests with stable diffusion models in production. We first comprehensively analyze …

Personalized recommendation is a ubiquitous appli-cation on the internet, with many
industries and hyperscalers extensively leveraging Deep Learning Recommendation …

Recommendation serving with deep learning models is one of the most valuable services of
modern E-commerce companies. In production, to accommodate billions of recommendation …

Efficiently serving embedding-based recommendation (EMR) models remains a significant
challenge due to their increasingly large memory requirements. Today's practice splits the …

Graph learning models have been widely deployed in collaborative filtering (CF) based
recommendation systems. Due to the issue of data sparsity, the graph structure of the …