相关论文: POLCA: Power Oversubscription in LLM Cloud Provide…

Large language models (LLMs) require enormous computing power to pretrain on massive datasets. When limited datasets are available, smaller-sized LLMs are better choice to pretrain (on user-specified datasets) by following the scaling laws…

Several scientific and industry applications require High Performance Computing (HPC) resources to process and/or simulate complex models. Not long ago, companies, research institutes, and universities used to acquire and maintain…

This paper considers a traditional problem of resource allocation, scheduling jobs on machines. One such recent application is cloud computing, where jobs arrive in an online fashion with capacity requirements and need to be immediately…

The common assumption in on-device AI is that GPUs, with their superior parallel processing, always provide the best performance for large language model (LLM) inference. In this work, we challenge this notion by empirically demonstrating…

The widespread use of cloud computing services is expected to increase the power consumed by ICT equipment in cloud computing environments rapidly. This paper first identifies the need of the collaboration among servers, the communication…

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference…

As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the quality and efficiency of the LLM post-training phase-including fine-tuning and inference,…

Transformer-based, pre-trained large language models (LLMs) have demonstrated outstanding performance across diverse domains, particularly in the emerging {\em pretrain-then-finetune} paradigm. Low-Rank Adaptation (LoRA), a…

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now scaling to trillions of parameters, has necessitated training across thousands of GPUs using complex hybrid parallelism strategies (e.g.,…

Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. However, the increasing size and complexity of LLMs present…

Serving machine learning inference workloads on the cloud is still a challenging task on the production level. Optimal configuration of the inference workload to meet SLA requirements while optimizing the infrastructure costs is highly…

Cloud computing is one of the rapidly improving technologies. It provides scalable resources needed for the ap- plications hosted on it. As cloud-based services become more dynamic, resource provisioning becomes more challenging. The QoS…

The ever increasing demand for ML-driven intelligence in a wide spectrum of domains has led to ubiquity of GPUs. At the same time, GPUs are notorious for their power consumption needs and often dominate power allocation in a typical ML…

Large Language Models (LLMs) exhibit remarkable human-like predictive capabilities. However, it is challenging to deploy LLMs to provide efficient and adaptive inference services at the edge. This paper proposes a novel Cloud-Edge…

Large Language Models (LLMs) are becoming the backbone of modern cloud services, yet their inference costs are dominated by GPU energy. Unlike traditional GPU workloads, LLM inference has two stages with different characteristics: the…

Power consumption in data centers has been growing significantly in recent years. To reduce power, servers are being equipped with increasingly sophisticated power management mechanisms. Different mechanisms offer dramatically different…

The recent growth of Artificial Intelligence (AI), particularly large language models, requires energy-demanding high-performance computing (HPC) data centers, which poses a significant burden on power system capacity. Scheduling data…

Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…

Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…