Related papers: FaaSTube: Optimizing GPU-oriented Data Transfer fo…
Cloud computing offers on-demand, scalable computing and storage, and has become an essential resource for the analyses of big biomedical data. The usual approach to cloud computing requires users to reserve and provision virtual servers.…
Serverless computing has recently experienced significant adoption by several applications, especially Internet of Things (IoT) applications. In serverless computing, rather than deploying and managing dedicated virtual machines, users are…
Modern Datalog engines (e.g., LogicBlox, Souffl\'e, ddlog) enable their users to write declarative queries which compute recursive deductions over extensional facts, leaving high-performance operationalization (query planning, semi-na\"ive…
Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This…
Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks, resulting in diverse and often conflicting Service Level…
Large-scale GPU clusters are widely-used to speed up both latency-critical (online) and best-effort (offline) deep learning (DL) workloads. However, most DL clusters either dedicate each GPU to one workload or share workloads in time,…
Serverless computing has emerged as a new paradigm for running short-lived computations in the cloud. Due to its ability to handle IoT workloads, there has been considerable interest in running serverless functions at the edge. However, the…
High performance is needed in many computing systems, from batch-managed supercomputers to general-purpose cloud platforms. However, scientific clusters lack elastic parallelism, while clouds cannot offer competitive costs for…
In this work, we propose FUSE, a novel GPU cache system that integrates spin-transfer torque magnetic random-access memory (STT-MRAM) into the on-chip L1D cache. FUSE can minimize the number of outgoing memory accesses over the…
Online analytical processing of queries on datasets in the many-terabyte range is only possible with costly distributed computing systems. To decrease the cost and increase the throughput, systems can leverage accelerators such as GPUs,…
Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…
Function-as-a-Service (FaaS) has become an increasingly popular way for users to deploy their applications without the burden of managing the underlying infrastructure. However, existing FaaS platforms rely on remote storage to maintain…
In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving…
GPU underutilization is a significant concern in many production deep learning clusters, leading to prolonged job queues and increased operational expenses. A promising solution to this inefficiency is GPU sharing, which improves resource…
Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the…
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…
Graphics Processing Units (GPUs) are becoming popular accelerators in modern High-Performance Computing (HPC) clusters. Installing GPUs on each node of the cluster is not efficient resulting in high costs and power consumption as well as…
Developing accurate and extendable performance models for serverless platforms, aka Function-as-a-Service (FaaS) platforms, is a very challenging task. Also, implementation and experimentation on real serverless platforms is both costly and…
The increasing use of hardware processing accelerators tailored for specific applications, such as the Vision Processing Unit (VPU) for image recognition, further increases developers' configuration, development, and management overhead.…
High-throughput physics experiments require efficient and increasingly complex real-time processing. This paper presents a modular, software-defined platform combining high-bandwidth PCIe digitizers with consumer GPUs to achieve continuous,…