English
Related papers

Related papers: CIDER: Boosting Memory-Disaggregated Key-Value Sto…

200 papers

Safe memory reclamation (SMR) schemes are an essential tool for lock-free data structures and concurrent programming. However, manual SMR schemes are notoriously difficult to apply correctly, and automatic schemes, such as reference…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-04-13 Daniel Anderson , Guy E. Blelloch , Yuanhao Wei

The linear growth of Key-Value (KV) cache remains a bottleneck for multi-turn LLM deployment. Existing KV cache compression methods often fail to account for the structural properties of multi-turn dialogues, relying on heuristic eviction…

Computation and Language · Computer Science 2026-01-30 Hong Chen , Xiang Liu , Bo Wang , Yuxuan Fan , Yuanlin Chu , Zongluo Li , Xiaowen Chu , Xuming Hu

In a distributed storage systems (DSS) with $k$ systematic nodes, robustness against node failure is commonly provided by storing redundancy in a number of other nodes and performing repair mechanism to reproduce the content of the failed…

Information Theory · Computer Science 2018-01-01 Kaveh Mahdaviani , Soheil Mohajer , Ashish Khisti

Dealing with the shear size and complexity of today's massive data sets requires computational platforms that can analyze data in a parallelized and distributed fashion. A major bottleneck that arises in such modern distributed computing…

Information Theory · Computer Science 2019-04-03 A. Salman Avestimehr , Seyed Mohammadreza Mousavi Kalan , Mahdi Soltanolkotabi

Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key-value (KV) cache, which stores attention keys and values to…

Computation and Language · Computer Science 2024-07-26 Zirui Liu , Jiayi Yuan , Hongye Jin , Shaochen Zhong , Zhaozhuo Xu , Vladimir Braverman , Beidi Chen , Xia Hu

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-11 Yanyu Liu , Jingying Fu , Sixiang Liu , Yitian Zou , You Fu , Jiehan Zhou , Shouhua Zhang

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts…

Machine Learning · Computer Science 2024-10-25 Yifei Yang , Zouying Cao , Qiguang Chen , Libo Qin , Dongjie Yang , Hai Zhao , Zhi Chen

As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…

Machine Learning · Computer Science 2025-12-09 Sourjya Roy , Shrihari Sridharan , Surya Selvam , Anand Raghunathan

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Xuyang Liu , Xiyan Gui , Yuchao Zhang , Linfeng Zhang

Memory-compute disaggregation promises transparent elasticity, high utilization and balanced usage for resources in data centers by physically separating memory and compute into network-attached resource "blades". However, existing designs…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-22 Seung-seob Lee , Yanpeng Yu , Yupeng Tang , Anurag Khandelwal , Lin Zhong , Abhishek Bhattacharjee

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Operating Systems · Computer Science 2026-01-21 Jing Zou , Shangyu Wu , Hancong Duan , Qiao Li , Chun Jason Xue

The growing scale of data requires efficient memory subsystems with large memory capacity and high memory performance. Disaggregated architecture has become a promising solution for today's cloud and edge computing for its scalability and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-28 Jing Wang , Chao Li , Taolei Wang , Jinyang Guo , Hanzhang Yang , Yiming Zhuansun , Minyi Guo

Transactional Memory (TM) is an approach aiming to simplify concurrent programming by automating synchronization while maintaining efficiency. TM usually employs the optimistic concurrency control approach, which relies on transactions…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-21 Paweł T. Wojciechowski , Konrad Siek

The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for…

Modern data-intensive applications face memory latency challenges exacerbated by disaggregated memory systems. Recent work shows that coroutines are promising in effectively interleaving tasks and hiding memory latency, but they struggle to…

Hardware Architecture · Computer Science 2025-11-20 Zhuolun Jiang , Songyue Wang , Xiaokun Pei , Tianyue Lu , Mingyu Chen

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a…

Computation and Language · Computer Science 2025-04-29 Ke Hong , Lufang Chen , Zhong Wang , Xiuhong Li , Qiuli Mao , Jianping Ma , Chao Xiong , Guanyu Wu , Buhe Han , Guohao Dai , Yun Liang , Yu Wang

Compute-in-memory (CiM) is a promising approach to improving the computing speed and energy efficiency in dataintensive applications. Beyond existing CiM techniques of bitwise logic-in-memory operations and dot product operations, this…

Hardware Architecture · Computer Science 2023-01-03 Yiming Chen , Yushen Fu , Mingyen Lee , Sumitha George , Yongpan Liu , Vijaykrishnan Narayanan , Huazhong Yang , Xueqing Li

Cache coherence scalability is a big challenge in shared memory systems. Traditional protocols do not scale due to the storage and traffic overhead of cache invalidation. Tardis, a recently proposed coherence protocol, removes cache…

Hardware Architecture · Computer Science 2016-07-28 Xiangyao Yu , Hongzhe Liu , Ethan Zou , Srinivas Devadas

In this paper, we consider an approach to the parallelizing of the algorithms realizing the modified probability changigng method with adaptation and partial rollback procedure for constrained pseudo-Boolean optimization problems. Existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-09-03 Lev Kazakovtsev

Memory disaggregation is an emerging data center architecture that improves resource utilization and scalability. Replication is key to ensure the fault tolerance of applications, but replicating shared data in disaggregated memory is hard.…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-25 Antoine Murat , Clément Burgelin , Athanasios Xygkis , Igor Zablotchi , Marcos K. Aguilera , Rachid Guerraoui