Related papers: Taming Request Imbalance: SLO-Aware Scheduling for…

An ongoing debate considers whether prefill-decode (PD) aggregation or disaggregation is superior for serving large language models (LLMs). This has driven optimizations for both approaches, each showing distinct advantages. This paper…

Large Language Models (LLMs) increasingly rely on inference-time reasoning algorithms such as chain-of-thought and multi-branch reasoning to improve accuracy on complex tasks. These methods, however, substantially increase token usage and…

The growing adoption of Large Language Models (LLMs) across various domains has driven the demand for efficient and scalable AI-serving solutions. Deploying LLMs requires optimizations to manage their significant computational and data…

Reinforcement Learning (RL) has emerged as a critical technique for advancing modern Large Language Models (LLMs), yet existing synchronous RL systems face severe performance bottlenecks. The rollout phase, which dominates end-to-end…

Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…

Training large language models (LLMs) increasingly relies on geographically distributed accelerators, causing prohibitive communication costs across regions and uneven utilization of heterogeneous hardware. We propose HALoS, a hierarchical…

Many emerging distributed applications, including big data analytics, generate a number of flows that concurrently transport data across data center networks. To improve their performance, it is required to account for the behavior of a…

Edge/fog computing, as a distributed computing paradigm, satisfies the low-latency requirements of ever-increasing number of IoT applications and has become the mainstream computing paradigm behind IoT applications. However, because large…

Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…

Low-earth-orbit (LEO) satellite communication networks have evolved into mega-constellations with hundreds to thousands of satellites inter-connecting with inter-satellite links (ISLs). Network planning, which plans for network resources…

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates substantial speedups…

On-device Large Language Models (LLMs) are transforming mobile AI, catalyzing applications like UI automation without privacy concerns. Nowadays the common practice is to deploy a single yet powerful LLM as a general task solver for…

This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…

Microservices architecture has become the dominant architecture in cloud computing paradigm with its advantages of facilitating development, deployment, modularity and scalability. The workflow of microservices architecture is transparent…

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like data…

The surging demand for GPUs in datacenters for machine learning (ML) has made efficient GPU utilization crucial. However, meeting the diverse needs of ML models while optimizing resource usage is challenging. To enable transparent,…

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Offloading large language models (LLMs) state to host memory during inference promises to reduce operational costs by supporting larger models, longer inputs, and larger batch sizes. However, the design of existing memory offloading…

Large Language Models (LLMs) have revolutionized numerous domains, driving the rise of Language-Model-as-a-Service (LMaaS) platforms that process millions of queries daily. These platforms must minimize latency and meet Service Level…