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

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficiently. However, standard MoEs enforce uniform expert sizes,creating a rigidity that fails to…

As Large Language Models (LLMs) continue to grow, reducing costs and alleviating GPU demands has become increasingly critical. However, existing schedulers primarily target either GPU compute or Key-Value Cache (KVC) utilization, failing to…

Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops,…

When output token counts can be predicted at submission time (Gan et al., 2026), client-side scheduling against a black-box LLM API becomes semi-clairvoyant: decisions condition on coarse token priors even though the provider's internals…

We formulate throughput maximizing, max-min fair, weighted max-min fair, and proportionally fair scheduling problems for cognitive radio networks managed by a centralized cognitive base station. We propose a very general scheduling model…

We address fair sensor scheduling over bandwidth-constrained communication channels. While existing literature on fair scheduling overlooks overall system efficiency, we introduce a novel $q$-fairness framework to balance efficiency and…

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…

Memory dominates datacenter system cost and power. Memory expansion via Compute Express Link (CXL) is an effective way to provide additional memory at lower cost and power, but its effective use requires software-level tiering for…

Mixture-of-Experts (MoE) model architecture has emerged as a promising solution for scaling transformer models efficiently, offering sparse activation that reduces computational costs while increasing model capacity. However, as MoE models…

Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacenters. An appealing alternative is to leverage collaborative…

Apache Spark is a widely adopted framework for large-scale data processing. However, in industrial analytics environments, Spark's built-in schedulers, such as FIFO and fair scheduling, struggle to maintain both user-level fairness and low…

Designing efficient and fair algorithms for sharing multiple resources between heterogeneous demands is becoming increasingly important. Applications include compute clusters shared by multi-task jobs and routers equipped with middleboxes…

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Efficient and fair allocation of multiple types of resources is a crucial objective in a cloud/distributed computing cluster. Users may have diverse resource needs. Furthermore, diversity in server properties/ capabilities may mean that…

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…

The Mixture of Experts (MoE) architecture has demonstrated significant advantages as it enables to increase the model capacity without a proportional increase in computation. However, the large MoE model size still introduces substantial…

Mixture of Experts (MoE) models have enabled the scaling of Large Language Models (LLMs) and Vision Language Models (VLMs) by achieving massive parameter counts while maintaining computational efficiency. However, MoEs introduce several…

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…

In this paper, we introduce an approach for application-aware resource block scheduling of elastic and inelastic adaptive real-time traffic in fourth generation Long Term Evolution (LTE) systems. The users are assigned to resource blocks. A…