English
Related papers

Related papers: Improving the Serving Performance of Multi-LoRA La…

200 papers

The memory-for-computation paradigm of KV caching is essential for accelerating large language model (LLM) inference service, but limited GPU high-bandwidth memory (HBM) capacity motivates offloading the KV cache to cheaper external storage…

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

Human Activity Recognition is a foundational task in pervasive computing. While recent advances in self-supervised learning and transformer-based architectures have significantly improved HAR performance, adapting large pretrained models to…

Machine Learning · Computer Science 2025-12-23 Irina Seregina , Philippe Lalanda , German Vega

Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key-value (KV) caches. Each visual input expands into thousands of tokens,…

Artificial Intelligence · Computer Science 2026-04-08 Bowen Zeng , Feiyang Ren , Jun Zhang , Xiaoling Gu , Ke Chen , Lidan Shou , Huan Li

We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance. QLoRA backpropagates gradients through a…

Machine Learning · Computer Science 2023-05-24 Tim Dettmers , Artidoro Pagnoni , Ari Holtzman , Luke Zettlemoyer

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-03-24 Yichun Xu , Navjot K. Khaira , Tejinder Singh

We study quality-latency-resource trade-offs in a documentation-grounded retrieval-augmented generation (RAG) system that uses Low-Rank Adaptation (LoRA) of the generator. We build a manually verified benchmark of 5,144 question-answer…

Computation and Language · Computer Science 2026-05-28 Evgenii Palnikov , Elizaveta Gavrilova

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

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with…

Machine Learning · Computer Science 2025-09-30 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Cache fusion accelerates generation process of LLMs equipped with RAG through KV caching and selective token recomputation, thereby reducing computational costs and improving efficiency. However, existing methods primarily rely on local…

Databases · Computer Science 2026-04-13 Jianxin Yan , Zeheng Qian , Wangze Ni , Zhitao Shen , Zhiping Wang , Haoyang Li , Jia Zhu , Lei Chen , Kui Ren

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-19 Jiaao He , Jidong Zhai

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Efficient real-world deployments of large language models (LLMs) rely on Key-Value (KV) caching for processing and generating long outputs, reducing the need for repetitive computation. For large contexts, Key-Value caches can take up tens…

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical…

Computation and Language · Computer Science 2025-06-10 Akshat Sharma , Hangliang Ding , Jianping Li , Neel Dani , Minjia Zhang

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

Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…

Machine Learning · Computer Science 2026-05-12 Xingyu Qu , Tianhao Lin , Yiqi Li , Zhiyu Chen , Sheng Wang

The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant…

Computation and Language · Computer Science 2024-07-19 Bingli Liao , Danilo Vasconcellos Vargas

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-04 Yifan Sun , Gholamreza Haffari , Minxian Xu , Rajkumar Buyya , Adel N. Toosi

Despite the success of the monolithic dense paradigm of large language models (LLMs), the LoRA adapters offer an efficient solution by fine-tuning small task-specific modules and merging them with the base model. However, in multi-task…

Machine Learning · Computer Science 2025-08-07 Zhan Su , Fengran Mo , Guojun Liang , Jinghan Zhang , Bingbing Wen , Prayag Tiwari , Jian-Yun Nie

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