Related papers: EdgeTran: Co-designing Transformers for Efficient …

Today, the rapid growth of applications reliant on datacenters calls for new advancements to meet the increasing traffic and computational demands. Traffic traces from datacenters are essential for further development and optimization of…

Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most appropriate model for each request based on accuracy and…

Transformer architectures have become the standard neural network model for various machine learning applications including natural language processing and computer vision. However, the compute and memory requirements introduced by…

The increased memory and processing capabilities of today's edge devices create opportunities for greater edge intelligence. In the domain of vision, the ability to adapt a Convolutional Neural Network's (CNN) structure and parameters to…

When trained as generative models, Deep Learning algorithms have shown exceptional performance on tasks involving high dimensional data such as image denoising and super-resolution. In an increasingly connected world dominated by mobile and…

This paper explores the performance of Google's Edge TPU on feed forward neural networks. We consider Edge TPU as a hardware platform and explore different architectures of deep neural network classifiers, which traditionally has been a…

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three…

Edge Federation is a new computing paradigm that seamlessly interconnects the resources of multiple edge service providers. A key challenge in such systems is the deployment of latency-critical and AI based resource-intensive applications…

In this paper, we propose a transfer learning (TL)-enabled edge-CNN framework for 5G industrial edge networks with privacy-preserving characteristic. In particular, the edge server can use the existing image dataset to train the CNN in…

We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers. MetaTT enables flexible and parameter-efficient model adaptation by using a single shared TT to factorize transformer sub-modules. This…

Multimodal foundation models are transformative in sequential recommender systems, leveraging powerful representation learning capabilities. While Parameter-efficient Fine-tuning (PEFT) is commonly used to adapt foundation models for…

Convolutional neural networks (CNNs) suffer from rapidly increasing storage and computational costs as their depth grows, which severely hinders their deployment on resource-constrained edge devices. Pruning is a practical approach for…

Neural network (NN) accelerators have been integrated into a wide-spectrum of computer systems to accommodate the rapidly growing demands for artificial intelligence (AI) and machine learning (ML) applications. NN accelerators share the…

Low-Latency IoT applications such as autonomous vehicles, augmented/virtual reality devices and security applications require high computation resources to make decisions on the fly. However, these kinds of applications cannot tolerate…

Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…

The proliferation of IoT devices in smart cities challenges 6G networks with conflicting energy-latency requirements across heterogeneous slices. Existing approaches struggle with the energy-latency trade-off, particularly for massive scale…

We present MegaTrain, a memory-centric system that efficiently trains 100B+ parameter large language models at full precision on a single GPU. Unlike traditional GPU-centric systems, MegaTrain stores parameters and optimizer states in host…

Generative transformer models have become increasingly complex, with large numbers of parameters and the ability to process multiple input modalities. Current methods for explaining their predictions are resource-intensive. Most crucially,…

Graphene field-effect transistors (GFETs) are experimental devices which are increasingly seeing commercial and research applications. Simulation and modelling forms an important stage in facilitating this transition, however the majority…

Large Transformer networks are increasingly used in settings where low inference latency can improve the end-user experience and enable new applications. However, autoregressive inference is resource intensive and requires parallelism for…