Related papers: SpotServe: Serving Generative Large Language Model…

Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV…

Cloud providers sell their idle capacity on markets through an auction-like mechanism to increase their return on investment. The instances sold in this way are called spot instances. In spite that spot instances are usually 90% cheaper…

Transient cloud servers such as Amazon Spot instances, Google Preemptible VMs, and Azure Low-priority batch VMs, can reduce cloud computing costs by as much as $10\times$, but can be unilaterally preempted by the cloud provider.…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs…

Recently, there has been an extensive research effort in building efficient large language model (LLM) inference serving systems. These efforts not only include innovations in the algorithm and software domains but also constitute…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

Infrastructure-as-a-Service providers are offering their unused resources in the form of variable-priced virtual machines (VMs), known as "spot instances", at prices significantly lower than their standard fixed-priced resources. To lease…

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache,…

Large Language Models (LLMs) are wildly popular today and it is important to serve them efficiently. Existing LLM serving systems are stateless across requests. Consequently, when LLMs are used in the common setting of multi-turn…

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a…

Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving…

In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the…

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 known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

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…

Large language model (LLM) inference often suffers from high latency, particularly in resource-constrained environments such as on-device or edge deployments. To address this challenge, we present StorInfer, a novel storage-assisted LLM…

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization…

Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared, heterogeneous hardware. This setting introduces new challenges for resource…