Related papers: Cronus: Efficient LLM inference on Heterogeneous G…

Prefill and decode (PD) disaggregation separates prompt prefill and token-by-token decode stages into distinct GPU pools and has become the dominant architecture for large-scale LLM serving in industry. Also, retrieval tasks via vector…

Training deep neural networks (DNNs) is a major workload in datacenters today, resulting in a tremendously fast growth of energy consumption. It is important to reduce the energy consumption while completing the DL training jobs early in…

Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption. While increasing parameter counts improves accuracy, it also broadens the gap between state-of-the-art capabilities and…

Heterogeneous computing integrates diverse processing elements, such as CPUs, GPUs, and FPGAs, within a single system, aiming to leverage the strengths of each architecture to optimize performance and energy consumption. In this context,…

Mixture-of-Experts (MoE) models offer computational efficiency during inference by activating only a subset of specialized experts for a given input. This enables efficient model scaling on multi-GPU systems that use expert parallelism…

Deep neural networks (DNNs) have been widely adopted for various mobile inference tasks, yet their ever-increasing computational demands are hindering their deployment on resource-constrained mobile devices. Hybrid deep learning partitions…

Agentic workflows carry out complex tasks by orchestrating multiple large language models (LLMs) and tools. Serving such workflows at a target throughput with low latency is challenging because they can be defined using arbitrary agentic…

As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…

Diffusion large language models (dLLMs) are emerging as a promising alternative to autoregressive models (ARMs) due to their ability to capture bidirectional context and the potential for parallel generation. Despite the advantages, dLLM…

In the context of Machine Learning as a Service (MLaaS) clouds, the extensive use of Large Language Models (LLMs) often requires efficient management of significant query loads. When providing real-time inference services, several…

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

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,…

The escalating adoption of diffusion models for applications such as image generation demands efficient parallel inference techniques to manage their substantial computational cost. However, existing diffusion parallelism inference schemes…

The rapid adoption of Large Language Models (LLMs) has made GPU inference efficiency an increasingly critical system concern. The runtime of LLM workloads is largely dominated by tile-based kernels, particularly General Matrix…

Edge computing enables latency-critical applications to process data close to end devices, yet task heterogeneity and limited resources pose significant challenges to efficient orchestration. This paper presents a measurement-driven,…

LLM inference powers latency-critical production services nowadays. The bursty nature of inference traffic results in over-provisioning, which in turn leads to resource underutilization. While online-offline colocation promises to utilize…

Advanced Large Language Models (LLMs) have achieved impressive performance across a wide range of complex and long-context natural language tasks. However, performing long-context LLM inference locally on a commodity GPU (a PC) with privacy…

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…

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…

GPUs are vastly underutilized, even when running resource-intensive AI applications, as GPU kernels within each job have diverse resource profiles that may saturate some parts of a device while often leaving other parts idle. Colocating…