English
Related papers

Related papers: TokenLake: A Unified Segment-level Prefix Cache Po…

200 papers

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Zuyan Liu , Benlin Liu , Jiahui Wang , Yuhao Dong , Guangyi Chen , Yongming Rao , Ranjay Krishna , Jiwen Lu

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

Computation and Language · Computer Science 2025-06-16 Jie Hu , Shengnan Wang , Yutong He , Ping Gong , Jiawei Yi , Juncheng Zhang , Youhui Bai , Renhai Chen , Gong Zhang , Cheng Li , Kun Yuan

Input data preprocessing is a common bottleneck when concurrently training multimedia machine learning (ML) models in modern systems. To alleviate these bottlenecks and reduce the training time for concurrent jobs, we present Seneca, a data…

Operating Systems · Computer Science 2025-11-19 Omkar Desai , Ziyang Jiao , Shuyi Pei , Janki Bhimani , Bryan S. Kim

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the…

Computation and Language · Computer Science 2024-08-09 Yilong Chen , Guoxia Wang , Junyuan Shang , Shiyao Cui , Zhenyu Zhang , Tingwen Liu , Shuohuan Wang , Yu Sun , Dianhai Yu , Hua Wu

The shift to data-intensive processing from the cloud to the edge has introduced new challenges and expectations for the next generation of intelligent computing systems. As the memory wall continues to grow, modern systems can only meet…

Hardware Architecture · Computer Science 2026-04-16 Denis Hoornaert , Cole Strickler , Manos Athanassoulis , Marco Caccamo , Heechul Yun , Renato Mancuso

The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods either sparsify the attention map with structured patterns or permanently evict tokens at…

Computation and Language · Computer Science 2026-05-04 Dongwon Jo , Beomseok Kang , Jiwon Song , Jae-Joon Kim

LLM inference serving typically scales out with a two-tier architecture: a cluster router distributes requests to multiple inference engines, each of which then in turn performs its own internal scheduling. However, this commonly used…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-02 Yue Zhang , Yuansheng Chen , Xuan Mo , Alex Xi , Jialun Li , WeiGang Wu

Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the next plan is…

Machine Learning · Computer Science 2026-04-28 Hojoon Kim , Yuheng Wu , Thierry Tambe

High Performance and Energy Efficiency are critical requirements for Internet of Things (IoT) end-nodes. Exploiting tightly-coupled clusters of programmable processors (CMPs) has recently emerged as a suitable solution to address this…

Hardware Architecture · Computer Science 2023-09-06 Jie Chen , Igor Loi , Eric Flamand , Giuseppe Tagliavini , Luca Benini , Davide Rossi

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Machine Learning · Computer Science 2023-09-13 Woosuk Kwon , Zhuohan Li , Siyuan Zhuang , Ying Sheng , Lianmin Zheng , Cody Hao Yu , Joseph E. Gonzalez , Hao Zhang , Ion Stoica

Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-09 Mohammadreza Malekabbasi , Minghe Wang , David Bermbach

Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they…

Cryptography and Security · Computer Science 2025-06-03 Jack Min Ong , Matthew Di Ferrante , Aaron Pazdera , Ryan Garner , Sami Jaghouar , Manveer Basra , Max Ryabinin , Johannes Hagemann

Shared memory multiprocessors come back to popularity thanks to rapid spreading of commodity multi-core architectures. As ever, shared memory programs are fairly easy to write and quite hard to optimise; providing multi-core programmers…

Distributed, Parallel, and Cluster Computing · Computer Science 2009-09-10 Marco Aldinucci , Massimo Torquati , Massimiliano Meneghin

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Computation and Language · Computer Science 2025-03-26 Joseph Sakau , Evander Kozlowski , Roderick Thistledown , Basil Steinberger

Enterprise data lakes often suffer from substantial amounts of duplicate and redundant data, with data volumes ranging from terabytes to petabytes. This leads to both increased storage costs and unnecessarily high maintenance costs for…

Distributing LLM inference across geographical regions can improve Time-to-First-Token (TTFT) by regionalizing service deployments. While existing multi-region load balancers save prefill computation by prioritizing Key--Value (KV) Cache…

Networking and Internet Architecture · Computer Science 2026-02-13 Alessio Ricci Toniolo , Abinaya Dinesh , Rome Thorstenson

The rapid growth of Web3.0 is transforming the Internet from a centralized structure to decentralized, which empowers users with unprecedented self-sovereignty over their own data. However, in the context of decentralized data access within…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-12 Jinyu Chen , Long Shi , Taotao Wang , Jiaheng Wang , Wei Zhang

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness…

Databases · Computer Science 2025-11-03 Chen Wang , Xunzhuo Liu , Yue Zhu , Alaa Youssef , Priya Nagpurkar , Huamin Chen

Our paper presents solutions using erasure coding, parallel connections to storage cloud and limited chunking (i.e., dividing the object into a few smaller segments) together to significantly improve the delay performance of uploading and…

Networking and Internet Architecture · Computer Science 2017-02-02 Guanfeng Liang , Ulas C. Kozat

In cellular networks, the densification of connected devices and base stations engender the ever-growing traffic intensity, and caching popular contents with smart management is a promising way to alleviate such consequences. Our research…

Information Theory · Computer Science 2021-03-25 Takehiro Ohashi