English
Related papers

Related papers: SAW-INT4: System-Aware 4-Bit KV-Cache Quantization…

200 papers

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…

Machine Learning · Computer Science 2025-04-29 Hanshi Sun , Li-Wen Chang , Wenlei Bao , Size Zheng , Ningxin Zheng , Xin Liu , Harry Dong , Yuejie Chi , Beidi Chen

Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV…

Machine Learning · Computer Science 2026-04-30 Zihan Zhao , Baotong Lu , Shengjie Lin , Yizou Chen , Jing Liu , Yanqi Zhang , Ziming Miao , Ming-Chang Yang , Haiying Shen , Qi Chen , Fan Yang

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) rely on Key-Value (KV) cache to reduce time-to-first-token (TTFT) latency, but existing disk-based KV cache systems using file-per-object layouts suffer from severe scalability bottlenecks due to file system…

Databases · Computer Science 2025-11-26 Weiping Yu , Ye Jiarui , He Mengke , Junfeng Liu , Siqiang Luo

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is significant and heavily impacts serving costs.…

Machine Learning · Computer Science 2026-04-28 Anastasiia Filippova , David Grangier , Marco Cuturi , João Monteiro

Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jonathan Cederlund , Axel Berg , Durmus Alp Emre Acar , Chuteng Zhou , Pontus Giselsson

Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memory size and bandwidth. The Key-Value (KV) cache size grows linearly with sequence length…

Machine Learning · Computer Science 2026-05-12 Junkai Zhang , Hang Guo , Luca Benini , Yawei Li

Large language models have revolutionized data processing in numerous domains, with their ability to handle extended context reasoning receiving notable recognition. To speed up inference, maintaining a key-value (KV) cache memory is…

Computation and Language · Computer Science 2024-10-22 Zhen Yang , J. N. Han , Kan Wu , Ruobing Xie , An Wang , Xingwu Sun , Zhanhui Kang

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on…

Machine Learning · Computer Science 2024-02-21 Yuxuan Yue , Zhihang Yuan , Haojie Duanmu , Sifan Zhou , Jianlong Wu , Liqiang Nie

Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns…

Machine Learning · Computer Science 2025-09-11 Bohan Yu , Yekun Chai

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

In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information…

Computation and Language · Computer Science 2025-05-16 Zefan Cai , Yichi Zhang , Bofei Gao , Yuliang Liu , Yucheng Li , Tianyu Liu , Keming Lu , Wayne Xiong , Yue Dong , Junjie Hu , Wen Xiao

Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory…

Computation and Language · Computer Science 2024-06-24 Jincheng Dai , Zhuowei Huang , Haiyun Jiang , Chen Chen , Deng Cai , Wei Bi , Shuming Shi

Deploying Small Language Models (SLMs) on edge platforms is critical for real-time, privacy-sensitive generative AI, yet constrained by memory, latency, and energy budgets. Quantization reduces model size and cost but suffers from device…

Machine Learning · Computer Science 2026-01-22 Nilesh Prasad Pandey , Jangseon Park , Onat Gungor , Flavio Ponzina , Tajana Rosing

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Machine Learning · Computer Science 2024-09-04 Yelysei Bondarenko , Riccardo Del Chiaro , Markus Nagel

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

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

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

Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors.…