Related papers: It Takes Two to Tango: Serverless Workflow Serving…

Serverless computing has seen rapid growth due to the ease-of-use and cost-efficiency it provides. However, function scheduling, a critical component of serverless systems, has been overlooked. In this paper, we take a first-principles…

In Function as a Service (FaaS), a serverless computing variant, customers deploy functions instead of complete virtual machines or Linux containers. It is the cloud provider who maintains the runtime environment for these functions. FaaS…

This paper explores resource allocation in serverless cloud computing platforms and proposes an optimization approach for autoscaling systems. Serverless computing relieves users from resource management tasks, enabling focus on application…

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…

Function-as-a-Service (FaaS) computing is an emerging cloud computing paradigm for its ease-of-management and elasticity. However, optimizing scheduling for serverless functions remains challenging due to their dynamic and event-driven…

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…

Function-as-a-Service (FaaS) platforms provide scalable and cost-efficient execution but suffer from increased latency and resource overheads in complex applications comprising multiple functions, particularly due to double billing when…

Cloud-based serverless computing systems, either public or privately provisioned, aim to provide the illusion of infinite resources and abstract users from details of the allocation decisions. With the goal of providing a low cost and a…

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…

Nowadays, large language models (LLMs) are published as a service and can be accessed by various applications via APIs, also known as language-model-as-a-service (LMaaS). Without knowing the generation length of requests, existing serving…

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…

As an emerging cloud computing deployment paradigm, serverless computing is gaining traction due to its efficiency and ability to harness on-demand cloud resources. However, a significant hurdle remains in the form of the cold start…

Function-as-a-Service (FaaS) is one of the most promising directions for the future of cloud services, and serverless functions have immediately become a new middleware for building scalable and cost-efficient microservices and…

Function-as-a-Service (FaaS) enables developers to run serverless applications without managing operational tasks. In current FaaS platforms, both synchronous and asynchronous calls are executed immediately. In this paper, we present…

Serverless computing eliminates infrastructure management overhead but introduces significant challenges regarding cold start latency and resource utilization. Traditional static resource allocation often leads to inefficiencies under…

In this paper, we introduce Janus, an autoregressive framework that unifies multimodal understanding and generation. Prior research often relies on a single visual encoder for both tasks, such as Chameleon. However, due to the differing…

Data loading has been one of the most common performance bottlenecks for many big data applications, especially when they are running on inefficient human-readable formats, such as JSON or CSV. Parsing, validating, integrity checking and…

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first…

Service Level Objectives (SLOs) aim to set threshold for service time in cloud services to ensure acceptable quality of service (QoS) and user satisfaction. Currently, many studies consider SLOs as a system resource to be allocated,…

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive…