相关论文: MUSE: Multi-Tenant Model Serving With Seamless Mod…
Sparsely-gated mixture-of-experts (MoE) has been widely adopted to scale deep learning models to trillion-plus parameters with fixed computational cost. The algorithmic performance of MoE relies on its token routing mechanism that forwards…
Mixture-of-Experts (MoE) models can scale parameter capacity by routing each token to a subset of experts through a learned gate function. While conditional routing reduces training costs, it shifts the burden on inference memory: expert…
Online multiple-output regression is an important machine learning technique for modeling, predicting, and compressing multi-dimensional correlated data streams. In this paper, we propose a novel online multiple-output regression method,…
Resource provisioning in multi-tenant stream processing systems faces the dual challenges of keeping resource utilization high (without over-provisioning), and ensuring performance isolation. In our common production use cases, where…
Modern multi-tenant, hardware-heterogeneous computing environments pose significant challenges for effective workload orchestration. Simple heuristics for assessing workload performance, such as CPU utilization or application-level metrics,…
Rapid advancements over the years have helped machine learning models reach previously hard-to-achieve goals, sometimes even exceeding human capabilities. However, to attain the desired accuracy, the model sizes and in turn their…
Accurate long-term trajectory prediction in complex scenes, where multiple agents (e.g., pedestrians or vehicles) interact with each other and the environment while attempting to accomplish diverse and often unknown goals, is a challenging…
Algorithmic fairness is often studied in static or single-agent settings, yet many real-world decision-making systems involve multiple interacting entities whose multi-stage actions jointly influence long-term outcomes. Existing fairness…
Timely resource allocation in edge-assisted vehicular networks is essential for compute-intensive services such as autonomous driving and navigation. However, vehicle mobility leads to spatio-temporal unpredictability of resource demands,…
In this paper, the Multi-stage Edge Server Upgrade (M-ESU) is proposed as a new network planning problem, involving the upgrading of an existing multi-access edge computing (MEC) system through multiple stages (e.g., over several years).…
In this paper, we present the practical problems and the lessons learned at short-video services from Kuaishou. In industry, a widely-used multi-task framework is the Mixture-of-Experts (MoE) paradigm, which always introduces some shared…
Memory tiering has received wide adoption in recent years as an effective solution to address the increasing memory demands of memory-intensive workloads. However, existing tiered memory systems often fail to meet service-level objectives…
This paper addresses the critical challenge of managing Quality of Service (QoS) in cloud services, focusing on the nuances of individual tenant expectations and varying Service Level Indicators (SLIs). It introduces a novel approach…
Timely updating of Internet of Things data is crucial for achieving immersion in vehicular metaverse services. However, challenges such as latency caused by massive data transmissions, privacy risks associated with user data, and…
Multi-access Edge Computing (MEC) is booming as a promising paradigm to push the computation and communication resources from cloud to the network edge to provide services and to perform computations. With container technologies, mobile…
The training of large-scale Mixture of Experts (MoE) models faces a critical memory bottleneck due to severe load imbalance caused by dynamic token routing. This imbalance leads to memory overflow on GPUs with limited capacity, constraining…
We consider a remote inference system with multiple modalities, where a multimodal machine learning (ML) model performs real-time inference using features collected from remote sensors. When sensor observations evolve dynamically over time,…
This paper presents the winning submission of the RaaVa team to the AmericasNLP 2025 Shared Task 3 on Automatic Evaluation Metrics for Machine Translation (MT) into Indigenous Languages of America, where our system ranked first overall…
The Mediation Information System Engineering project is currently finishing its second iteration (MISE 2.0). The main objective of this scientific project is to provide any emerging collaborative situation with methods and tools to deploy a…
We study how queue-state information disclosures affect impatient tenants in multi-tenant edge systems. We propose an information-bulletin strategy in which each queue periodically broadcasts two Markov models. One is a model of…