English
Related papers

Related papers: Titanus: Enabling KV Cache Pruning and Quantizatio…

200 papers

Transformer-based Large Language Models rely critically on the KV cache to efficiently handle extended contexts during the decode phase. Yet, the size of the KV cache grows proportionally with the input length, burdening both memory…

Computation and Language · Computer Science 2025-08-14 Payman Behnam , Yaosheng Fu , Ritchie Zhao , Po-An Tsai , Zhiding Yu , Alexey Tumanov

Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to compress KV cache is quantization. However, traditional…

Machine Learning · Computer Science 2024-07-19 Amir Zandieh , Majid Daliri , Insu Han

Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in significant memory consumption and I/O bottlenecks. Previous KV…

Computation and Language · Computer Science 2025-01-28 Zunhai Su , Wang Shen , Linge Li , Zhe Chen , Hanyu Wei , Huangqi Yu , Kehong Yuan

Across large language model (LLM) applications, we observe an emerging trend for reusing KV caches to save the prefill delays of processing repeated input texts in different LLM inputs. This has led to a broad design space, including…

Networking and Internet Architecture · Computer Science 2025-03-20 Hanchen Li , Yuhan Liu , Yihua Cheng , Kuntai Du , Junchen Jiang

Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-11 Zaifeng Pan , Ajjkumar Patel , Zhengding Hu , Yipeng Shen , Yue Guan , Wan-Lu Li , Lianhui Qin , Yida Wang , Yufei Ding

Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior work shows that attention is dominated by a small subset of…

Machine Learning · Computer Science 2026-04-21 Nazmul Takbir , Hamidreza Alikhani , Nikil Dutt , Sangeetha Abdu Jyothi

The linear growth of key-value (KV) cache memory and quadratic computational in attention mechanisms complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization…

Computation and Language · Computer Science 2025-10-07 Xin Liu , Xudong Wang , Pei Liu , Guoming Tang

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or…

Hardware Architecture · Computer Science 2024-10-17 Lian Liu , Haimeng Ren , Long Cheng , Zhaohui Xu , Yudong Pan , Mengdi Wang , Xiaowei Li , Yinhe Han , Ying Wang

Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer key-value caches. We observe that this limit applies to a strictly weaker problem than the…

Machine Learning · Computer Science 2026-04-20 Gregory Magarshak

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model…

Computation and Language · Computer Science 2026-05-14 Shiyu Ji , Yixuan Wang , Yijun Liu , Qingfu Zhu , Wanxiang Che

Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasible, existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-19 Sabiha Afroz , Redwan Ibne Seraj Khan , Hadeel Albahar , Jingoo Han , Ali R. Butt

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization,…

Machine Learning · Computer Science 2026-03-03 Ngoc Bui , Shubham Sharma , Simran Lamba , Saumitra Mishra , Rex Ying

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when…

Machine Learning · Computer Science 2025-04-07 Jiayi Yao , Hanchen Li , Yuhan Liu , Siddhant Ray , Yihua Cheng , Qizheng Zhang , Kuntai Du , Shan Lu , Junchen Jiang

Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drastically speed up…

Computation and Language · Computer Science 2023-08-30 Yury Zemlyanskiy , Michiel de Jong , Luke Vilnis , Santiago Ontañón , William W. Cohen , Sumit Sanghai , Joshua Ainslie

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Machine Learning · Computer Science 2025-11-10 Pratik Poudel

Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important…

Machine Learning · Computer Science 2026-03-24 Ruijie Miao , Zhiming Wang , Wang Li , Shiwei Wu , Shufan Liu , Yanbing Jiang , Tong Yang

Large Language Models (LLMs) suffer inference-time memory bottlenecks dominated by the attention Key-Value (KV) cache, which scales with model size and context length. While KV-cache quantization alleviates this cost, bit allocation between…

Machine Learning · Computer Science 2026-05-12 Mohsen Hariri , Alan Luo , Weicong Chen , Shaochen Zhong , Tianyi Zhang , Qifan Wang , Xia Hu , Xiaotian Han , Vipin Chaudhary

This paper presents Thanos, a novel weight-pruning algorithm designed to reduce the memory footprint and enhance the computational efficiency of large language models (LLMs) by removing redundant weights while maintaining accuracy. Thanos…

Machine Learning · Computer Science 2025-04-09 Ivan Ilin , Peter Richtarik

In this work we show that the size versus accuracy trade-off of neural network quantization can be significantly improved by increasing the quantization dimensionality. We propose the GPTVQ method, a new fast method for post-training vector…

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann
‹ Prev 1 8 9 10 Next ›