Fs-real: Towards real-world cross-device federated learning
Federated Learning (FL) aims to train high-quality models in collaboration with distributed
clients while not uploading their local data, which attracts increasing attention in both …
clients while not uploading their local data, which attracts increasing attention in both …
Fusionai: Decentralized training and deploying llms with massive consumer-level gpus
The rapid growth of memory and computation requirements of large language models
(LLMs) has outpaced the development of hardware, hindering people who lack large-scale …
(LLMs) has outpaced the development of hardware, hindering people who lack large-scale …
Ideal: Toward high-efficiency device-cloud collaborative and dynamic recommendation system
Recommendation systems have shown great potential to solve the information explosion
problem and enhance user experience in various online applications, which recently …
problem and enhance user experience in various online applications, which recently …
On-device learning for model personalization with large-scale cloud-coordinated domain adaption
Cloud-based learning is currently the mainstream in both academia and industry. However,
the global data distribution, as a mixture of all the users' data distributions, for training a …
the global data distribution, as a mixture of all the users' data distributions, for training a …
Achelous: Enabling Programmability, Elasticity, and Reliability in Hyperscale Cloud Networks
C Wei, X Li, Y Yang, X Jiang, T Xu, B Yang… - Proceedings of the …, 2023 - dl.acm.org
Cloud computing has witnessed tremendous growth, prompting enterprises to migrate to the
cloud for reliable and on-demand computing. Within a single Virtual Private Cloud (VPC) …
cloud for reliable and on-demand computing. Within a single Virtual Private Cloud (VPC) …
Aztr: Aerial video action recognition with auto zoom and temporal reasoning
We propose a novel approach for aerial video action recognition. Our method is designed
for videos captured using UAVs and can run on edge or mobile devices. We present a …
for videos captured using UAVs and can run on edge or mobile devices. We present a …
V10: Hardware-Assisted NPU Multi-tenancy for Improved Resource Utilization and Fairness
Modern cloud platforms have deployed neural processing units (NPUs) like Google Cloud
TPUs to accelerate online machine learning (ML) inference services. To improve the …
TPUs to accelerate online machine learning (ML) inference services. To improve the …
Fs-real: A real-world cross-device federated learning platform
Federated learning (FL) is a general distributed machine learning paradigm that provides
solutions for tasks where data cannot be shared directly. Due to the difficulties in …
solutions for tasks where data cannot be shared directly. Due to the difficulties in …
DC-CCL: Device-Cloud Collaborative Controlled Learning for Large Vision Models
Many large vision models have been deployed on the cloud for real-time services.
Meanwhile, fresh samples are continuously generated on the served mobile device. How to …
Meanwhile, fresh samples are continuously generated on the served mobile device. How to …
InferFair: Towards QoS-aware scheduling for performance isolation guarantee in heterogeneous model serving systems
Y Peng, H Peng - Future Generation Computer Systems, 2024 - Elsevier
With the popularity of Deep Neural Network (DNN) models in diverse fields, DNN inference
services have been widely deployed on cloud for resource-limited devices to support …
services have been widely deployed on cloud for resource-limited devices to support …