English
Related papers

Related papers: Understanding Bottlenecks for Efficiently Serving …

200 papers

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the…

Computation and Language · Computer Science 2026-01-29 Zeyu Xing , Xing Li , Hui-Ling Zhen , Mingxuan Yuan , Sinno Jialin Pan

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

Machine Learning · Computer Science 2025-05-30 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Michael W. Mahoney , Yakun Sophia Shao , Kurt Keutzer , Amir Gholami

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Machine Learning · Computer Science 2026-05-21 Dean Calver

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However,…

Computation and Language · Computer Science 2026-03-12 Konrad Staniszewski , Adrian Łańcucki

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-04-14 Yuzhen Mao , Qitong Wang , Martin Ester , Ke Li

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…

Hardware Architecture · Computer Science 2025-04-23 Rui Xie , Asad Ul Haq , Linsen Ma , Yunhua Fang , Zirak Burzin Engineer , Liu Liu , Tong Zhang

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

As the field of Large Language Models (LLMs) continues to evolve, the context length in inference is steadily growing. Key-Value Cache (KVCache), the intermediate representations of tokens within LLM inference, has now become the primary…

Computation and Language · Computer Science 2025-04-01 Hailin Zhang , Xiaodong Ji , Yilin Chen , Fangcheng Fu , Xupeng Miao , Xiaonan Nie , Weipeng Chen , Bin Cui

Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially on consumer-grade hardware. Mixture of Experts (MoE) models provide an efficient…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-19 En-Ming Huang , Li-Shang Lin , Chun-Yi Lee

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead…

Computation and Language · Computer Science 2024-12-13 Meizhi Zhong , Xikai Liu , Chen Zhang , Yikun Lei , Yan Gao , Yao Hu , Kehai Chen , Min Zhang

Large Language Models (LLMs) are increasingly deployed in complex multi-agent applications that rely on external function calls. This workload creates severe performance challenges for the KV Cache: spatial contention leads to the eviction…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-21 Zhuohang Bian , Feiyang Wu , Zhuoran Li , Teng Ma , Youwei Zhuo

As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-30 Yongchao He , Bohan Zhao , Zheng Cao

Modern Large Language Model serving system batches multiple requests to achieve high throughput, while batching attention operations is challenging, rendering memory bandwidth a critical bottleneck. The community relies on high-end GPUs…

Hardware Architecture · Computer Science 2025-05-15 Minsu Kim , Seongmin Hong , RyeoWook Ko , Soongyu Choi , Hunjong Lee , Junsoo Kim , Joo-Young Kim , Jongse Park

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Computation and Language · Computer Science 2025-07-24 Luoyang Sun , Cheng Deng , Jiwen Jiang , Xinjian Wu , Haifeng Zhang , Lei Chen , Lionel Ni , Jun Wang

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

Computation and Language · Computer Science 2025-02-06 You Wu , Haoyi Wu , Kewei Tu

Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's…

Computation and Language · Computer Science 2024-11-21 Luohe Shi , Hongyi Zhang , Yao Yao , Zuchao Li , Hai Zhao

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store…

Computation and Language · Computer Science 2024-06-06 Dongjie Yang , XiaoDong Han , Yan Gao , Yao Hu , Shilin Zhang , Hai Zhao

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Machine Learning · Computer Science 2024-06-13 Harry Dong , Xinyu Yang , Zhenyu Zhang , Zhangyang Wang , Yuejie Chi , Beidi Chen

LLM inference is constrained by GPU memory capacity and bandwidth. Tiered memory architectures mitigate this by allowing the GPU to offload memory to the remote tier. However, existing memory offloading frameworks rely on prefetching data…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-30 Shouxu Lin , Zhiyuan Guo , Jiaxin Lin