相关论文: On-Demand Multi-Task Sparsity for Efficient Large-…
Task-based programming models have proven to be a robust and versatile way to approach development of applications for distributed environments. They provide natural programming patterns with high performance. However, execution on this…
Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities but impose substantial computational and latency burdens, posing critical challenges for deployment on resource-constrained edge devices. In this…
To circumvent persistent connectivity to the cloud infrastructure, the current emphasis on computing at network edge devices in the multi-robot domain is a promising enabler for delay-sensitive jobs, yet its adoption is rife with…
Running multiple deep neural networks (DNNs) in parallel has become an emerging workload in both edge devices, such as mobile phones where multiple tasks serve a single user for daily activities, and data centers, where various requests are…
In this paper, task offloading from vehicles with random velocities is optimized via a novel dynamic programming framework. Particularly, in a vehicular network with multiple vehicles and base stations (BSs), computing tasks of vehicles are…
Task-based runtime systems provide flexible load balancing and portability for parallel scientific applications, but their strong scaling is highly sensitive to task granularity. As parallelism increases, scheduling overhead may transition…
We present a framework for performance optimization in serverless edge-cloud platforms using dynamic task placement. We focus on applications for smart edge devices, for example, smart cameras or speakers, that need to perform processing…
While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…
Edge computing is an emerging paradigm to enable low-latency applications, like mobile augmented reality, because it takes the computation on processing devices that are closer to the users. On the other hand, the need for highly scalable…
In the Multi-task Learning (MTL) framework, every task demands distinct feature representations, ranging from low-level to high-level attributes. It is vital to address the specific (feature/parameter) needs of each task, especially in…
The advent of vehicle autonomy, connectivity and electric powertrains is expected to enable the deployment of Autonomous Mobility-on-Demand systems. Crucially, the routing and charging activities of these fleets are impacted by the design…
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,…
Task offloading to mobile edge computing (MEC) has emerged as a key technology to alleviate the computation workloads of mobile devices and decrease service latency for the computation-intensive applications. Device battery consumption is…
Handling the ever-increasing complexity of mesh generation codes along with the intricacies of newer hardware often results in codes that are both difficult to comprehend and maintain. Different facets of codes such as thread management and…
Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…
Edge computing has become increasingly popular across many domains and enterprises. However, given the locality constraint of edges (i.e., only close-by edges are useful), multiplexing diverse workloads becomes challenging. This results in…
Artificial intelligence workloads, especially transformer models, exhibit emergent sparsity in which computations perform selective sparse access to dense data. The workloads are inefficient on hardware designed for dense computations and…
Continual learning on edge devices poses unique challenges due to stringent resource constraints. This paper introduces a novel method that leverages stochastic competition principles to promote sparsity, significantly reducing deep network…
Mobile edge computing (MEC) is one of the promising solutions to process computational-intensive tasks for the emerging time-critical Internet-of-Things (IoT) use cases, e.g., virtual reality (VR), augmented reality (AR), autonomous…
Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for…