Related papers: PROSERVE: Unified Multi-Priority Request Schedulin…

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…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

This paper proposes a hierarchical solution to scale streaming services across quality and resource dimensions. Modern scenarios, like smart cities, heavily rely on the continuous processing of IoT data to provide real-time services and…

In today's enterprise storage systems, supported data services such as snapshot delete or drive rebuild can cause tremendous performance interference if executed inline along with heavy foreground IO, often leading to missing SLOs (Service…

Existing Large Language Model (LLM) serving systems prioritize maximum throughput. They often neglect Service Level Objectives (SLOs) such as Time to First Token (TTFT) and Time Per Output Token (TPOT), which leads to suboptimal SLO…

Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long…

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…

We consider a distributed server system consisting of a large number of servers, each with limited capacity on multiple resources (CPU, memory, disk, etc.). Jobs with different rewards arrive over time and require certain amounts of…

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a…

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and…

Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-thought generation. However, RL training efficiency is often…

Network slicing is a critical driver for guaranteeing the diverse service level agreements (SLA) in 5G and future networks. Inter-slice radio resource allocation (IS-RRA) in the radio access network (RAN) is very important. However, user…

Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to…

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual…

We present a new framework for designing nonpreemptive and job-size oblivious scheduling policies in the multiserver-job queueing model. The main requirement is to identify a static and balanced sub-partition of the server set and ensure…

Recent developments in large language models (LLMs) have demonstrated their remarkable proficiency in a range of tasks. Compared to in-house homogeneous GPU clusters, deploying LLMs in cloud environments with diverse types of GPUs is…

Diffusion models have emerged as the prevailing approach for text-to-image (T2I) and text-to-video (T2V) generation, yet production platforms must increasingly serve both modalities on shared GPU clusters while meeting stringent latency…

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…

Efficient scheduling is crucial for interactive Large Language Model (LLM) applications, where low request completion time directly impacts user engagement. Size-based scheduling algorithms like Shortest Remaining Process Time (SRPT) aim to…

Service supply chain management is to prepare spare parts for failed products under warranty. Their goal is to reach agreed service level at the minimum cost. We convert this business problem into a preference based multi-objective…