English
Related papers

Related papers: PipeMax: Enhancing Offline LLM Inference on Commod…

200 papers

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-23 Yihao Zhao , Jiadun Chen , Peng Sun , Lei Li , Xuanzhe Liu , Xin Jin

Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-01 Yi-Chien Lin , Woosuk Kwon , Ronald Pineda , Fanny Nina Paravecino

The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurate, and widely generalizable GPU performance models to…

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Xiaoniu Song , Zihang Zhong , Rong Chen , Haibo Chen

We introduce Model-Distributed Inference for Large-Language Models (MDI-LLM), a novel framework designed to facilitate the deployment of state-of-the-art large-language models (LLMs) across low-power devices at the edge. This is…

Machine Learning · Computer Science 2025-05-27 Davide Macario , Hulya Seferoglu , Erdem Koyuncu

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…

Operating Systems · Computer Science 2025-03-07 Hongchao Du , Shangyu Wu , Arina Kharlamova , Nan Guan , Chun Jason Xue

Personalized recommendation is a ubiquitous application on the internet, with many industries and hyperscalers extensively leveraging Deep Learning Recommendation Models (DLRMs) for their personalization needs (like ad serving or movie…

Hardware Architecture · Computer Science 2024-10-30 Rishabh Jain , Vivek M. Bhasi , Adwait Jog , Anand Sivasubramaniam , Mahmut T. Kandemir , Chita R. Das

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across…

Machine Learning · Computer Science 2025-12-08 Yuhan Liu , Yihua Cheng , Jiayi Yao , Yuwei An , Xiaokun Chen , Shaoting Feng , Yuyang Huang , Samuel Shen , Rui Zhang , Kuntai Du , Junchen Jiang

Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits…

Computation and Language · Computer Science 2024-11-19 Yungi Kim , Hyunsoo Ha , Seonghoon Yang , Sukyung Lee , Jihoo Kim , Chanjun Park

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even…

Hardware Architecture · Computer Science 2023-06-12 Yunho Jin , Chun-Feng Wu , David Brooks , Gu-Yeon Wei

We introduce Glinthawk, an architecture for offline Large Language Model (LLM) inference. By leveraging a two-tiered structure, Glinthawk optimizes the utilization of the high-end accelerators ("Tier 1") by offloading the attention…

Machine Learning · Computer Science 2025-02-12 Pouya Hamadanian , Sadjad Fouladi

Pipeline parallelism is widely used to scale the training of transformer-based large language models, various works have been done to improve its throughput and memory footprint. In this paper, we address a frequently overlooked issue: the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Man Tsung Yeung , Penghui Qi , Min Lin , Xinyi Wan

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-11 Ilias Bournias , Lukas Cavigelli , Georgios Zacharopoulos

Distributed prefix caching has become a core technique for efficient LLM serving. However, for long-context requests with high cache hit ratios, retrieving reusable KVCache blocks from remote servers has emerged as a new performance…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-24 Weiye Wang , Chen Chen , Junxue Zhang , Zhusheng Wang , Hui Yuan , Zixuan Guan , Xiaolong Zheng , Qizhen Weng , Yin Chen , Minyi Guo

In this paper, we propose LoopLynx, a scalable dataflow architecture for efficient LLM inference that optimizes FPGA usage through a hybrid spatial-temporal design. The design of LoopLynx incorporates a hybrid temporal-spatial architecture,…

Hardware Architecture · Computer Science 2025-04-15 Jianing Zheng , Gang Chen

Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-cost edge devices with tight memory constraints. Expert offloading mitigates…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-04 Liujianfu Wang , Yuyang Du , Yuchen Pan , Soung Chang Liew , Jiacheng Liu , Kexin Chen

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

Performance · Computer Science 2026-04-21 Mao Lin , Xi Wang , Guilherme Cox , Dong Li , Hyeran Jeon

In large language model (LLM) serving systems, executing each request consists of two phases: the compute-intensive prefill phase and the memory-intensive decoding phase. To prevent performance interference between the two phases, current…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-27 Yunkai Liang , Zhangyu Chen , Pengfei Zuo , Zhi Zhou , Xu Chen , Zhou Yu

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-25 Fengyao Bai , Hongbin Zhang , Zhitao Chen , Jiangsu Du , Zhiguang Chen , Yutong Lu