Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML
applications, the number of different ML inference systems has exploded. Over 100 …

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 …

With its huge real-world demands, large-scale confidential computing still cannot be
supported by today's Trusted Execution Environment (TEE), due to the lack of scalable and …

Privacy and security have rapidly emerged as first order design constraints. Users now
demand more protection over who can see their data (confidentiality) as well as how it is …

Video sharing (eg, YouTube, Vimeo, Facebook, TikTok) accounts for the majority of internet
traffic, and video processing is also foundational to several other key workloads (video …

In this paper, we provide a deep dive into the deployment of inference accelerators at
Facebook. Many of our ML workloads have unique characteristics, such as sparse memory …

In two-party machine learning prediction services, the client's goal is to query a remote
server's trained machine learning model to perform neural network inference in some …

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

Many active learning and search approaches are intractable for large-scale industrial
settings with billions of unlabeled examples. Existing approaches search globally for the …

The Visual Multimethod Assessment Fusion (VMAF) algorithm has recently emerged as a
state-of-the-art approach to video quality prediction, that now pervades the streaming and …