Related papers: Queue management for slo-oriented large language m…

Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving instances can improve resource utilization, but directly…

With the rapid development of IT operations, it has become increasingly crucial to efficiently manage and analyze large volumes of data for practical applications. The techniques of Natural Language Processing (NLP) have shown remarkable…

Large language models (LLMs) are increasingly used in applications forming multi-request workflows like document summarization, search-based copilots, and multi-agent programming. While these workflows unlock richer functionality, they also…

The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly…

Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory…

Being more powerful and intrusive into user-device interactions, LLMs are eager for on-device execution to better preserve user privacy. In this work, we propose a new paradigm of mobile AI: LLM as a system service on mobile devices…

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Deploying million-token Large Language Models (LLMs) is challenging because production workloads are highly heterogeneous, mixing short queries and long documents. This heterogeneity, combined with the quadratic complexity of attention,…

Large language model (LLM) applications are blindfolded to the infrastructure underneath and generate tokens autoregressively, indifferent to the system load, thus risking inferencing latency inflation and poor user experience. Our…

With the increasing complexity and rapid expansion of the scale of AI systems in cloud platforms, the log data generated during system operation is massive, unstructured, and semantically ambiguous, which brings great challenges to fault…

In the upcoming 6G era, vehicular networks are shifting from simple Vehicle-to-Vehicle (V2V) communication to the more complex Vehicle-to-Everything (V2X) connectivity. At the forefront of this shift is the incorporation of Large Language…

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.…

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators…

Supply chain operations traditionally involve a variety of complex decision making problems. Over the last few decades, supply chains greatly benefited from advances in computation, which allowed the transition from manual processing to…

With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process:…

As Large Language Models (LLMs) gain traction, their reliance on power-hungry GPUs places ever-increasing energy demands, raising environmental and monetary concerns. Inference dominates LLM workloads, presenting a critical challenge for…

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the computational demands…

While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…

Applications based on Large Language Models (LLMs) contains a series of tasks to address real-world problems with boosted capability, which have dynamic demand volumes on diverse backends. Existing serving systems treat the resource demands…