Related papers: Equinox: Holistic Fair Scheduling in Serving Large…

Large Language Models (LLMs) are demonstrating rapid improvements on complex reasoning benchmarks, particularly when allowed to utilize intermediate reasoning steps before converging on a final solution. However, current literature often…

Modern computing systems increasingly rely on composing heterogeneous devices to improve performance and efficiency. Programming these systems is often unproductive: algorithm implementations must be coupled to system-specific logic,…

Online marketplaces use rating systems to promote the discovery of high-quality products. However, these systems also lead to high variance in producers' economic outcomes: a new producer who sells high-quality items, may unluckily receive…

Machine learning (ML) inference serving systems host deep neural network (DNN) models and schedule incoming inference requests across deployed GPUs. However, limited support for task prioritization and insufficient latency estimation under…

While the large energy consumption of Large Language Models (LLMs) is recognized by the community, system operators lack guidance for energy-efficient LLM inference deployments that leverage energy trade-offs of heterogeneous hardware due…

As machine learning systems become increasingly integrated into high-stakes decision-making processes, ensuring fairness in algorithmic outcomes has become a critical concern. Methods to mitigate bias typically fall into three categories:…

A supervised machine learning algorithm determines a model from a learning sample that will be used to predict new observations. To this end, it aggregates individual characteristics of the observations of the learning sample. But this…

Recent decades have witnessed the tremendous development of network science, which indeed brings a new and insightful language to model real systems of different domains. Betweenness, a widely employed centrality in network science, is a…

Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in…

Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints.…

LLM agents, which often comprise parallel inference tasks, are commonly adopted to solve real-world problems. When serving such task-parallel LLM agents in shared GPU servers, the scheduler is expected to attain fast agent completion with…

In an attempt to make algorithms fair, the machine learning literature has largely focused on equalizing decisions, outcomes, or error rates across race or gender groups. To illustrate, consider a hypothetical government rideshare program…

Universities face surging applications and heightened expectations for fairness, making accurate admission prediction increasingly vital. This work presents a comprehensive framework that fuses machine learning, deep learning, and large…

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster.…

A new class of multi agent single machine scheduling problems is introduced, where each job is associated with a self interested agent with a utility function decreasing in completion time. We aim to achieve a fair solution by maximizing…

Although High Performance Computing (HPC) users understand basic resource requirements such as the number of CPUs and memory limits, internal infrastructural utilization data is exclusively leveraged by cluster operators, who use it to…

We study fair allocation of constrained resources, where a market designer optimizes overall welfare while maintaining group fairness. In many large-scale settings, utilities are not known in advance, but are instead observed after…

We present fast, fair, flexible, and welfare efficient algorithms for assigning reviewers to submitted conference papers. Our approaches extend picking sequence mechanisms, standard tools from the fair allocation literature to ensure…

Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE…

Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs. We introduce EfficientLLM, a novel benchmark and the first…