English
Related papers

Related papers: Tail-Optimized Caching for LLM Inference

200 papers

As large language models (LLMs) improve their capabilities in handling complex tasks, the issues of computational cost and efficiency due to long prompts are becoming increasingly prominent. To accelerate model inference and reduce costs,…

Computation and Language · Computer Science 2024-09-04 Xuechen Liang , Meiling Tao , Yinghui Xia , Tianyu Shi , Jun Wang , JingSong Yang

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

Cryptography and Security · Computer Science 2025-10-22 Linke Song , Zixuan Pang , Wenhao Wang , Zihao Wang , XiaoFeng Wang , Hongbo Chen , Wei Song , Yier Jin , Dan Meng , Rui Hou

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…

Computation and Language · Computer Science 2024-07-02 Bin Gao , Zhuomin He , Puru Sharma , Qingxuan Kang , Djordje Jevdjic , Junbo Deng , Xingkun Yang , Zhou Yu , Pengfei Zuo

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…

Machine Learning · Computer Science 2024-12-10 Weizhuo Li , Zhigang Wang , Yu Gu , Ge Yu

Caching systems using the Least Recently Used (LRU) principle have now become ubiquitous. A fundamental question for these systems is whether the cache space should be pooled together or divided to serve multiple flows of data item requests…

Performance · Computer Science 2017-08-08 Jian Tan , Guocong Quan , Kaiyi Ji , Ness Shroff

Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to…

Software Engineering · Computer Science 2026-01-23 Yi Zhai , Dian Shen , Junzhou Luo , Bin Yang

Large Language Models (LLMs) have become increasingly popular, transforming a wide range of applications across various domains. However, the real-world effectiveness of their query cache systems has not been thoroughly investigated. In…

Computation and Language · Computer Science 2024-06-04 Jiaxing Li , Chi Xu , Feng Wang , Isaac M von Riedemann , Cong Zhang , Jiangchuan Liu

Web proxies such as NGINX commonly rely on least-recently-used (LRU) eviction, which is size agnostic and can thrash under periodic bursts and mixed object sizes. We introduce Cold-RL, a learned eviction policy for NGINX that replaces LRU's…

Machine Learning · Computer Science 2025-08-19 Aayush Gupta , Arpit Bhayani

Caching plays a crucial role in networking systems to reduce the load on the network and is commonly employed by content delivery networks (CDNs) in order to improve performance. One of the commonly used mechanisms, Least Recently Used…

Networking and Internet Architecture · Computer Science 2019-06-25 Eric Friedlander , Vaneet Aggarwal

Last level caches (LLCs) occupy a large chip-area and there size is expected to grow further to offset the limitations of memory bandwidth and speed. Due to high leakage consumption of SRAM device, caches designed with SRAM consume large…

Hardware Architecture · Computer Science 2014-08-12 Sparsh Mittal

As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for reducing inference costs and latency. Existing caching…

Machine Learning · Computer Science 2026-04-23 Baran Atalar , Xutong Liu , Jinhang Zuo , Siwei Wang , Wei Chen , Carlee Joe-Wong

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Information Retrieval · Computer Science 2026-04-06 Cornelius Kummer , Lena Jurkschat , Michael Färber , Sahar Vahdati

Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is…

Machine Learning · Computer Science 2023-08-30 Banghua Zhu , Ying Sheng , Lianmin Zheng , Clark Barrett , Michael I. Jordan , Jiantao Jiao

Commonly used caching policies, such as LRU (Least Recently Used) or LFU (Least Frequently Used), exhibit optimal performance only under specific traffic patterns. Even advanced machine learning-based methods, which detect patterns in…

Machine Learning · Computer Science 2024-06-18 Damiano Carra , Giovanni Neglia

Large language models (LLMs) have achieved huge success in numerous natural language process (NLP) tasks. However, it faces the challenge of significant resource consumption during inference. In this paper, we aim to improve the inference…

Computation and Language · Computer Science 2024-02-05 Hanlin Zhu , Banghua Zhu , Jiantao Jiao

Clients are evolving beyond chat completion, and now include a variety of innovative inference-time scaling and deep reasoning techniques. At the same time, inference servers remain heavily optimized for chat completion. Prior work has…

Artificial Intelligence · Computer Science 2025-11-05 Paul Castro , Nick Mitchell , Nathan Ordonez , Thomas Parnell , Mudhakar Srivatsa , Antoni Viros i Martin

While Deep Learning (DL) technologies are a promising tool to solve networking problems that map to classification tasks, their computational complexity is still too high with respect to real-time traffic measurements requirements. To…

Networking and Internet Architecture · Computer Science 2022-10-04 Alessandro Finamore , James Roberts , Massimo Gallo , Dario Rossi

Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are…

Machine Learning · Computer Science 2026-02-10 Ziyao Tang , Pengkun Jiao , Xinhang Chen , Wei Liu , Shiyong Li , Jingjing Chen

In Large Language Model (LLM) serving, the KV-cache (KVC) bottleneck causes high tail Time-to-First-Token (TTFT) and Time-Between-Tokens (TBT), impairing user experience, particularly in time-sensitive applications. However, satisfying both…

Computation and Language · Computer Science 2025-03-26 Haiying Shen , Tanmoy Sen , Masahiro Tanaka