Related papers: LLM-Driven Intent-Based Privacy-Aware Orchestratio…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Modern cloud platforms increasingly host large-scale deep learning (DL) workloads, demanding high-throughput, low-latency GPU scheduling. However, the growing heterogeneity of GPU clusters and limited visibility into application…

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…

Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contending with constrained memory availability and heterogeneous hardware targets. To realize this…

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by…

This paper introduces an efficient Vision-Language Model (VLM) pipeline specifically optimized for deployment on embedded devices, such as those used in robotics and autonomous driving. The pipeline significantly reduces the computational…

Large language model (LLM) services are mostly centralized, leading to scalability bottlenecks and underutilization of substantial scattered GPU resources. While decentralization offers a promising alternative, existing frameworks primarily…

Large Language Models (LLMs) have shown remarkable proficiency in natural language understanding (NLU), opening doors for innovative applications. We introduce StreamLink - an LLM-driven distributed data system designed to improve the…

Efficient LLM inference is critical for real-world applications, especially within heterogeneous GPU clusters commonly found in organizations and on-premise datacenters as GPU architecture rapidly evolves. Current disaggregated prefill…

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…

We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Prompt tokens determine initial KV usage, and each…

With the rapid innovation of GPUs, heterogeneous GPU clusters in both public clouds and on-premise data centers have become increasingly commonplace. In this paper, we demonstrate how pipeline parallelism, a technique wellstudied for…

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…

Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to deploy and fine-tune LLMs on mobile edge devices with…

We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing models into online scenarios: (1) limited…

To alleviate hardware scarcity in training large deep neural networks (DNNs), particularly large language models (LLMs), we present FusionLLM, a decentralized training system designed and implemented for training DNNs using geo-distributed…

We investigate the feasibility of using Multimodal Large Language Models (MLLMs) for real-time online episodic memory question answering. While cloud offloading is common, it raises privacy and latency concerns for wearable assistants,…

Emerging reconfigurable datacenters allow to dynamically adjust the network topology in a demand-aware manner. These datacenters rely on optical switches which can be reconfigured to provide direct connectivity between racks, in the form of…

Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs, aiming to select the best-performing LLMs tailored to the domains of user queries, while managing computational resources. However,…

Modern large language foundation models (LLM) have now entered the daily lives of millions of users. We ask a natural question whether it is possible to customize LLM for every user or every task. From system and industrial economy…