Related papers: SynerDiff: Synergetic Continuous Batching for Fast…
Cooperative inference in Mobile Edge Computing (MEC), achieved by deploying partitioned Deep Neural Network (DNN) models between resource-constrained user equipments (UEs) and edge servers (ESs), has emerged as a promising paradigm.…
Performance optimization is the art of continuous seeking a harmonious mapping between the application domain and hardware. Recent years have witnessed a surge of deep learning (DL) applications in industry. Conventional wisdom for…
MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used as a latent MF by leveraging the pre-trained Stable…
A recent study has shown that diffusion models are well-suited for modeling the generative process of user-item interactions in recommender systems due to their denoising nature. However, existing diffusion model-based recommender systems…
Parallel applications often rely on work stealing schedulers in combination with fine-grained tasking to achieve high performance and scalability. However, reducing the total energy consumption in the context of work stealing runtimes is…
Current techniques and systems for distributed model training mostly assume that clusters are comprised of homogeneous servers with a constant resource availability. However, cluster heterogeneity is pervasive in computing infrastructure,…
Diffusion models have achieved remarkable success in image generation but their practical application is often hindered by the slow sampling speed. Prior efforts of improving efficiency primarily focus on compressing models or reducing the…
Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…
Services hosted in multi-tenant cloud platforms often encounter performance interference due to contention for non-partitionable resources, which in turn causes unpredictable behavior and degradation in application performance. To grapple…
Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its…
In this work, we propose a content caching and delivery strategy to maximize throughput capacity in cache-enabled wireless networks. To this end, efficient betweenness (EB), which indicates the ratio of content delivery paths passing…
Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A…
AI-Generated Content (AIGC), as a novel manner of providing Metaverse services in the forthcoming Internet paradigm, can resolve the obstacles of immersion requirements. Concurrently, edge computing, as an evolutionary paradigm of computing…
Having large batch sizes is one of the most critical aspects of increasing the accelerator efficiency and the performance of DNN model inference. However, existing model serving systems cannot achieve adequate batch sizes while meeting…
Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world…
A growing number of critical workflow applications leverage a streamlined edge-hub-cloud architecture, which diverges from the conventional edge computing paradigm. An edge device, in collaboration with a hub device and a cloud server,…
Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells…
Text-to-image (T2I) generation using diffusion models has become a blockbuster service in today's AI cloud. A production T2I service typically involves a serving workflow where a base diffusion model is augmented with various "add-on"…
Data engineering workflows require reliable differencing across files, databases, and query outputs, yet existing tools falter under schema drift, heterogeneous types, and limited explainability. SmartDiff is a unified system that combines…
Distributed computing systems often consist of hundreds of nodes, executing tasks with different resource requirements. Efficient resource provisioning and task scheduling in such systems are non-trivial and require close monitoring and…