English
Related papers

Related papers: Chameleon: Adaptive Caching and Scheduling for Man…

200 papers

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…

Machine Learning · Computer Science 2024-09-19 Zhengmao Ye , Dengchun Li , Zetao Hu , Tingfeng Lan , Jian Sha , Sicong Zhang , Lei Duan , Jie Zuo , Hui Lu , Yuanchun Zhou , Mingjie Tang

The potential harms of the under-representation of minorities in training data, particularly in multi-modal settings, is a well-recognized concern. While there has been extensive effort in detecting such under-representation, resolution has…

Machine Learning · Computer Science 2024-12-03 Mahdi Erfanian , H. V. Jagadish , Abolfazl Asudeh

In modern server CPUs, the Last-Level Cache (LLC) serves not only as a victim cache for higher-level private caches but also as a buffer for low-latency DMA transfers between CPU cores and I/O devices through Direct Cache Access (DCA).…

Hardware Architecture · Computer Science 2025-06-16 Haneul Park , Jiaqi Lou , Sangjin Lee , Yifan Yuan , Kyoung Soo Park , Yongseok Son , Ipoom Jeong , Nam Sung Kim

The rapid adoption of Large Language Models (LLMs) has driven a growing demand for efficient inference, particularly in latency-sensitive applications such as chatbots and personalized assistants. Unlike traditional deep neural networks,…

Hardware Architecture · Computer Science 2025-10-06 Shubham Negi , Kaushik Roy

Recent advances in low-rank adaptation (LoRA) have enabled efficient fine-tuning of large language models (LLMs) with minimal additional parameters. However, existing LoRA methods apply static rank configurations uniformly across all input…

Computation and Language · Computer Science 2026-01-30 Ketan Thakkar , Maitreyi Chatterjee , Ramasubramanian Balasubramanian , Achyuthan Jootoo , Rajendra Ugrani

LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from…

Machine Learning · Computer Science 2026-05-08 Shen Xu , Xiangwen Zhuge , Zhe Xu , Yingkun Hu , Zheng Yang , Yunhao Liu

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-14 Wei Da , Evangelia Kalyvianaki

As program workloads (e.g., AI) increase in size and algorithmic complexity, the primary challenge lies in their high dimensionality, encompassing computing cores, array sizes, and memory hierarchies. To overcome these obstacles, innovative…

Hardware Architecture · Computer Science 2025-10-10 Jinwei Tang , Jiayin Qin , Nuo Xu , Pragnya Sudershan Nalla , Yu Cao , Yang , Zhao , Caiwen Ding

Computer systems are becoming increasingly heterogeneous with the emergence of new memory technologies and compute devices. GPUs alongside CPUs have become commonplace and CXL is poised to be a mainstay of cloud systems. The operating…

Operating Systems · Computer Science 2024-01-18 Aditya K Kamath , Sujay Yadalam

The use of Large Language Models (LLMs) for querying relational data has given rise to relQuery, a workload pattern that applies templated LLM calls to structured tables. As relQuery services become more widely adopted in applications such…

Databases · Computer Science 2026-01-21 Xin Zhang , Shihong Gao , Yanyan Shen , Haoyang Li , Lei Chen

Serving Large Language Models (LLMs) efficiently in multi-region setups remains a challenge. Due to cost and GPU availability concerns, providers typically deploy LLMs in multiple regions using instance with long-term commitments, like…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-10 Tian Xia , Ziming Mao , Jamison Kerney , Ethan J. Jackson , Zhifei Li , Jiarong Xing , Scott Shenker , Ion Stoica

Edge deployment of large language models (LLMs) increasingly relies on libraries of lightweight LoRA adapters, yet GPU/DRAM can keep only a small resident subset at a time. Serving a request through a non-resident adapter requires paging…

Machine Learning · Computer Science 2026-04-21 Shaoang Li , Jian Li

The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent…

Hardware Architecture · Computer Science 2026-01-29 Yanru Chen , Runyang Tian , Yue Pan , Zheyu Li , Weihong Xu , Tajana Rosing

Large language models (LLMs) have revolutionized applications such as code completion, chatbots, and online classification. To elevate user experiences, service level objectives (SLOs) serve as crucial benchmarks for assessing inference…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-13 Jinqi Huang , Yi Xiong , Xuebing Yu , Wenjie Huang , Entong Li , Li Zeng , Xin Chen

Large Language Models (LLMs), such as GPT and LLaMA, introduce unique memory access characteristics during inference due to frequent token sequence lookups and embedding vector retrievals. These workloads generate highly irregular and…

Hardware Architecture · Computer Science 2025-12-17 Songze Liu , Hongkun Du , Shaowen Wang

Recent developments in large language models (LLMs) have demonstrated their remarkable proficiency in a range of tasks. Compared to in-house homogeneous GPU clusters, deploying LLMs in cloud environments with diverse types of GPUs is…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-07 Youhe Jiang , Fangcheng Fu , Xiaozhe Yao , Taiyi Wang , Bin Cui , Ana Klimovic , Eiko Yoneki

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Multimedia · Computer Science 2025-03-12 Jianian Zhu , Hang Wu , Haojie Wang , Yinghui Li , Biao Hou , Ruixuan Li , Jidong Zhai

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…

Machine Learning · Computer Science 2025-04-11 Jianqiao Wangni