English
Related papers

Related papers: ForkKV: Scaling Multi-LoRA Agent Serving via Copy-…

200 papers

Key-value (KV) caching has emerged as a crucial optimization technique for accelerating inference in large language models (LLMs). By allowing the attention operation to scale linearly rather than quadratically with the total sequence…

Computation and Language · Computer Science 2026-01-06 Gopi Krishna Jha , Sameh Gobriel , Liubov Talamanova , Nilesh Jain

Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge to the inference system. Eviction methods have revealed the…

Computation and Language · Computer Science 2025-07-10 Zicong Tang , Shi Luohe , Zuchao Li , Baoyuan Qi , Guoming Liu , Lefei Zhang , Ping Wang

Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challenging, particularly in resource-constrained environments.…

Machine Learning · Computer Science 2025-09-12 Hao Zhang , Bo Huang , Zhenjia Li , Xi Xiao , Hui Yi Leong , Zumeng Zhang , Xinwei Long , Tianyang Wang , Hao Xu

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

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Computation and Language · Computer Science 2025-06-16 Manlai Liang , Wanyi Huang , Mandi Liu , Huaijun Li , Jinlong Li

The rise of million-token, agent-based applications has placed unprecedented demands on large language model (LLM) inference services. The long-running nature of these tasks increases their susceptibility to hardware and software faults,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-05 Shakya Jayakody , Youpeng Zhao , Chinmay Dhanraj Nehate , Jun Wang

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model…

Computation and Language · Computer Science 2024-04-15 Shichen Dong , Wen Cheng , Jiayu Qin , Wei Wang

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes…

Machine Learning · Computer Science 2026-05-22 Bin Yang , Qiuyu Leng , Jun Zeng , Zhenhua Wu

Large Language Models(LLMs) have had a profound impact on AI applications, particularly in the domains of long-text comprehension and generation. KV Cache technology is one of the most widely used techniques in the industry. It ensures…

Computation and Language · Computer Science 2024-04-30 Qiaozhi He , Zhihua Wu

Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden largely restricts the application of LLMs especially when one…

Machine Learning · Computer Science 2023-10-10 Yuhui Xu , Lingxi Xie , Xiaotao Gu , Xin Chen , Heng Chang , Hengheng Zhang , Zhengsu Chen , Xiaopeng Zhang , Qi Tian

Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token…

The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global…

Machine Learning · Computer Science 2026-05-25 Junzhe Yang , Xiaoyu Shen

We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficiency by restricting each layer update to a fixed low-rank form, but this static…

Machine Learning · Computer Science 2026-05-12 Omatharv Bharat Vaidya , Connor T. Jerzak , Nhat Ho , Chandrajit Bajaj

Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during…

Hardware Architecture · Computer Science 2026-04-08 Oteo Mamo , Olga Kogiou , Hyunjin Yi , Weikuan Yu

Traditional KV cache eviction strategies, which discard less critical KV-pairs based on attention scores, often degrade generation quality, causing context loss or hallucinations. Recent efforts shift toward KV merging, merging eviction…

Computation and Language · Computer Science 2025-11-14 Kunxi Li , Yufan Xiong , Zhonghua Jiang , Yiyun Zhou , Zhaode Wang , Chengfei Lv , Shengyu Zhang

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…

Computation and Language · Computer Science 2025-03-21 Shibo Jie , Yehui Tang , Kai Han , Zhi-Hong Deng , Jing Han

Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM) architectures demonstrate superior energy efficiency due to…

Computation and Language · Computer Science 2026-03-10 Taiqiang Wu , Chenchen Ding , Wenyong Zhou , Yuxin Cheng , Xincheng Feng , Shuqi Wang , Wendong Xu , Chufan Shi , Zhengwu Liu , Ngai Wong

Low-Rank Adaptation (LoRA) has emerged as one of the most effective, computationally tractable fine-tuning approaches for training Vision-Language Models (VLMs) and Large Language Models (LLMs). LoRA accomplishes this by freezing the…

Machine Learning · Computer Science 2025-05-28 Nastaran Saadati , Zhanhong Jiang , Joshua R. Waite , Shreyan Ganguly , Aditya Balu , Chinmay Hegde , Soumik Sarkar

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Hardware Architecture · Computer Science 2025-09-16 Yunhua Fang , Rui Xie , Asad Ul Haq , Linsen Ma , Kaoutar El Maghraoui , Naigang Wang , Meng Wang , Liu Liu , Tong Zhang

As large-scale language models continue to scale up in both size and context length, the memory and communication cost of key-value (KV) cache storage has become a major bottleneck in multi-GPU and multi-node inference. While MoE-based…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-20 Dong Liu , Yanxuan Yu , Ben Lengerich , Ying Nian Wu
‹ Prev 1 8 9 10 Next ›