Related papers: RecPipe: Co-designing Models and Hardware to Joint…

This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform. In such platforms, low latency is critical to enhance user experiences. However,…

Pipeline parallelism is an essential distributed parallelism method. Increasingly complex and diverse DNN models necessitate meticulously customized pipeline schedules for performance. However, existing practices typically rely on…

Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many…

Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem. To tackle this, the pre-training mechanism has been widely adopted, which attempts to leverage large-scale…

Recommender systems are inherently dynamic feedback loops where prolonged local interactions accumulate into macroscopic structural degradation such as information cocoons. Existing representation learning paradigms are universally…

We present the design and implementation of a RAG-based AI system benchmarking (RAGPerf) framework for characterizing the system behaviors of RAG pipelines. To facilitate detailed profiling and fine-grained performance analysis, RAGPerf…

Region proposal is critical for object detection while it usually poses a bottleneck in improving the computation efficiency on traditional control-flow architectures. We have observed region proposal tasks are potentially suitable for…

The increasing heterogeneity of high-performance computing (HPC) systems and the transition to exascale architectures require systematic and reproducible performance evaluation across diverse workloads. While continuous integration (CI)…

With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face…

System level synthesis enables improved robust MPC formulations by allowing for joint optimization of the nominal trajectory and controller. This paper introduces a tailored algorithm for solving the corresponding disturbance feedback…

Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…

Recently, Mixture-of-Experts (MoE) has become one of the most popular techniques to scale pre-trained models to extraordinarily large sizes. Dynamic activation of experts allows for conditional computation, increasing the number of…

This paper presents a deployed, production-grade system designed to enhance and scale search query datasets for intent-based recommendation systems in digital banking. In real-world environments, the growing volume and complexity of user…

High Performance Computing (HPC) platforms allow scientists to model computationally intensive algorithms. HPC clusters increasingly use General-Purpose Graphics Processing Units (GPGPUs) as accelerators; FPGAs provide an attractive…

To address increasing compute demand from recent multi-model workloads with heavy models like large language models, we propose to deploy heterogeneous chiplet-based multi-chip module (MCM)-based accelerators. We develop an advanced…

Recommender system based on historical user-item interactions is of vital importance for web-based services. However, the observed data used to train the recommender model suffers from severe bias issues. Practically, the item frequency…

The sequential recommendation aims to recommend items, such as products, songs and places, to users based on the sequential patterns of their historical records. Most existing sequential recommender models consider the next item prediction…

The deep learning accelerator is one of the methods to accelerate deep learning network computations, which is mainly based on convolutional neural network acceleration. To address the fact that concurrent convolutional neural network…

High-Performance Computing (HPC) platforms enable scientific software to achieve breakthroughs in many research fields such as physics, biology, and chemistry, by employing Research Software Engineering (RSE) techniques. These include 1)…

In this paper, we present sequeval, a software tool capable of performing the offline evaluation of a recommender system designed to suggest a sequence of items. A sequence-based recommender is trained considering the sequences already…