The emerging field of artificial intelligence of things (AIoT, AI+ IoT) is driven by the
widespread use of intelligent infrastructures and the impressive success of deep learning …

Artificial General Intelligence (AGI), possessing the capacity to comprehend, learn, and
execute tasks with human cognitive abilities, engenders significant anticipation and intrigue …

We study fusion for deep neural networks (DNNs) in a just-in-time (JIT) compilation
framework Apollo. It considers both memory-and compute-bound tensor operators for fusion …

Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …

This work reveals that memory-intensive computation is a rising performance-critical factor in
recent machine learning models. Due to a unique set of new challenges, existing ML …

Minimizing monetary cost and maximizing the goodput of inference serving systems are
increasingly important with the ever-increasing popularity of deep learning models. While it …

We study embedding table placement for distributed recommender systems, which aims to
partition and place the tables on multiple hardware devices (eg, GPUs) to balance the …

Large models are widely used in intelligent transportation systems (ITS) and autonomous
vehicles (AV) due to their excellent new capabilities such as intelligence emergence …

Abstract Graph Neural Networks (GNNs) have been widely used in various domains, and
GNNs with sophisticated computational graph lead to higher latency and larger memory …

With the increasing size of DNN models and the growing discrepancy between compute
performance and memory bandwidth, fusing multiple layers together to reduce off-chip …