Related papers: Serverless inferencing on Kubernetes
Spatiotemporal data are being produced in continuously growing volumes by a variety of data sources and a variety of application fields rely on rapid analysis of such data. Existing systems such as PostGIS or MobilityDB usually build on…
Inference serving is of great importance in deploying machine learning models in real-world applications, ensuring efficient processing and quick responses to inference requests. However, managing resources in these systems poses…
Recent trends in Web development demonstrate an increased interest in serverless applications, i.e. applications that utilize computational resources provided by cloud services on demand instead of requiring traditional server management.…
As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…
Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…
Processing long temporal sequences is a key challenge in deep learning. In recent years, Transformers have become state-of-the-art for this task, but suffer from excessive memory requirements due to the need to explicitly store the…
A typical setup in many machine learning scenarios involves a server that holds a model and a user that possesses data, and the challenge is to perform inference while safeguarding the privacy of both parties. Private Inference has been…
Modern edge applications demand novel solutions where edge applications do not have to rely on a single cloud provider (which cannot be in the vicinity of every edge device) or dedicated edge servers (which cannot scale as clouds) for…
AI research often emphasizes model design and algorithmic performance, while deployment and inference remain comparatively underexplored despite being critical for real-world use. This study addresses that gap by investigating the…
Serverless computing provides just-in-time infrastructure provisioning with rapid elasticity and a finely-grained pricing model. As full control of resource allocation is in the hands of the cloud provider and applications only consume…
Serverless computing has rapidly emerged as a popular cloud computing paradigm. It enables developers to implement function-level tasks, i.e., serverless functions, without managing infrastructure. While reducing operational overhead, it…
Foundation models (FMs) unlock unprecedented multimodal and multitask intelligence, yet their cloud-centric deployment precludes real-time responsiveness and compromises user privacy. Meanwhile, monolithic execution at the edge remains…
We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering…
The recent advances in LLMs bring a strong demand for efficient system support to improve overall serving efficiency. As LLM inference scales towards multiple GPUs and even multiple compute nodes, various coordination patterns, such as…
Today data is often scattered among billions of resource-constrained edge devices with security and privacy constraints. Federated Learning (FL) has emerged as a viable solution to learn a global model while keeping data private, but the…
We propose a server-based approach to manage a general-purpose graphics processing unit (GPU) in a predictable and efficient manner. Our proposed approach introduces a GPU server that is a dedicated task to handle GPU requests from other…
Dynamic offloading of Machine Learning (ML) model partitions across different resource orchestration services, such as Function-as-a-Service (FaaS) and Infrastructure-as-a-Service (IaaS), can balance processing and transmission delays while…
Serverless computing and stream processing represent two dominant paradigms for event-driven data processing, yet both make assumptions that render them inefficient for short-running, lightweight, and unpredictable streams that require…
Serverless Computing is a computing paradigm that provides efficient infrastructure management and elastic scalability. Serverless functions scale up or down based on demand, which means that functions are not directly addressable and rely…
The rise of serverless computing introduced a new class of scalable, elastic and widely available parallel workers in the cloud. Many systems and applications benefit from offloading computations and parallel tasks to dynamically allocated…