English
Related papers

Related papers: FastSwitch: Optimizing Context Switching Efficienc…

200 papers

Large language model (LLM) inference systems face a fundamental tension between minimizing Time-to-First-Token (TTFT) latency for new requests and maintaining a high, steady token generation rate (low Time-Per-Output-Token, or TPOT) for…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-17 Hongtao Lyu , Boyue Liu , Mingyu Wu , Haibo Chen

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

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use…

Machine Learning · Computer Science 2024-09-26 Bingyang Wu , Yinmin Zhong , Zili Zhang , Shengyu Liu , Fangyue Liu , Yuanhang Sun , Gang Huang , Xuanzhe Liu , Xin Jin

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Machine Learning · Computer Science 2025-10-06 Junyi Chen , Chuheng Du , Renyuan Liu , Shuochao Yao , Dingtian Yan , Jiang Liao , Shengzhong Liu , Fan Wu , Guihai Chen

The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly…

Artificial Intelligence · Computer Science 2025-05-01 Azam Ikram , Xiang Li , Sameh Elnikety , Saurabh Bagchi

The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-Forward Networks (FFNs) dominate this cost, accounting for…

Machine Learning · Computer Science 2026-02-03 Aayush Gautam , Mukul Gagrani , Junyoung Park , Mingu Lee , Chiris Lott , Narasimha Reddy

In long-context Large Language Model (LLM) inference, the Time-To-First-Token (TTFT) latency incurred by the prefill stage has become the foremost bottleneck limiting interactive performance and deployment cost. KV Cache reuse offers a…

Hardware Architecture · Computer Science 2026-05-26 Fei li , Song Liu , Yan Liu , Jinhua Cui , Shiqiang Nie , Jinyu Wang , Weiguo Wu

High-demand LLM inference services (e.g., ChatGPT and BARD) support a wide range of requests from short chat conversations to long document reading. To ensure that all client requests are processed fairly, most major LLM inference services…

Artificial Intelligence · Computer Science 2024-06-06 Ying Sheng , Shiyi Cao , Dacheng Li , Banghua Zhu , Zhuohan Li , Danyang Zhuo , Joseph E. Gonzalez , Ion Stoica

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

Large language model (LLM) inference serving systems are essential to various LLM-based applications. As demand for LLM services continues to grow, scaling these systems to handle high request rates while meeting latency Service-Level…

Machine Learning · Computer Science 2025-04-11 Shihong Gao , Xin Zhang , Yanyan Shen , Lei Chen

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Artificial Intelligence · Computer Science 2025-05-27 Ahmet Caner Yüzügüler , Jiawei Zhuang , Lukas Cavigelli

Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. We introduce FastMem, a novel method…

Computation and Language · Computer Science 2024-10-08 Junyi Zhu , Shuochen Liu , Yu Yu , Bo Tang , Yibo Yan , Zhiyu Li , Feiyu Xiong , Tong Xu , Matthew B. Blaschko

Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference…

The expanding context windows in large language models (LLMs) have greatly enhanced their capabilities in various applications, but they also introduce significant challenges in maintaining low latency, particularly in Time to First Token…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-10 Yi Xiong , Hao Wu , Changxu Shao , Ziqing Wang , Rui Zhang , Yuhong Guo , Junping Zhao , Ke Zhang , Zhenxuan Pan

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Machine Learning · Computer Science 2026-04-21 Dongwon Jo , Jiwon Song , Yulhwa Kim , Jae-Joon Kim

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal…

Performance · Computer Science 2024-11-01 Youpeng Zhao , Jun Wang

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-04 Yifan Sun , Gholamreza Haffari , Minxian Xu , Rajkumar Buyya , Adel N. Toosi

Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve…

Hardware Architecture · Computer Science 2025-05-08 Hang Zhang , Jiuchen Shi , Yixiao Wang , Quan Chen , Yizhou Shan , Minyi Guo

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

Hardware Architecture · Computer Science 2025-08-13 Ming-Yen Lee , Faaiq Waqar , Hanchen Yang , Muhammed Ahosan Ul Karim , Harsono Simka , Shimeng Yu

Serving long-context LLMs is challenging because request lengths and batch composition vary during token generation, causing the memory footprint to fluctuate significantly at runtime. Offloading KV caches to host memory limits effective…

Artificial Intelligence · Computer Science 2026-03-03 Xinyue Ma , Heelim Hong , Taegeon Um , Jongseop Lee , Seoyeong Choy , Woo-Yeon Lee , Myeongjae Jeon
‹ Prev 1 2 3 10 Next ›