English
Related papers

Related papers: A First Look At Efficient And Secure On-Device LLM…

200 papers

Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating…

Computation and Language · Computer Science 2025-10-15 Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Yue Liu , Bo Li , Xuming Hu , Xiaowen Chu

The widespread deployment of LLMs across enterprise services has created a critical security blind spot. Organizations operate multiple LLM services handling billions of queries daily, yet regulatory compliance boundaries prevent these…

Cryptography and Security · Computer Science 2026-03-03 Waris Gill , Natalie Isak , Matthew Dressman

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple…

Computation and Language · Computer Science 2025-11-11 Jingbo Yang , Bairu Hou , Wei Wei , Yujia Bao , Shiyu Chang

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…

Efficient deployment of Large Language Models (LLMs) requires batching multiple requests together to improve throughput. As the batch size, context length, or model size increases, the size of the key and value (KV) cache can quickly become…

Machine Learning · Computer Science 2024-05-08 Tianyi Zhang , Jonah Yi , Zhaozhuo Xu , Anshumali Shrivastava

Mixed-precision inference techniques reduce the memory and computational demands of Large Language Models (LLMs) by applying hybrid precision formats to model weights, activations, and KV caches. However, existing systems struggle to (i)…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Li Zhang , Youhe Jiang , Guoliang He , Xin Chen , Han Lv , Qian Yao , Ningsheng Ma , Fangcheng Fu , Kai Chen

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

Hardware Architecture · Computer Science 2026-04-29 Mingbo Hao , Changwei Yan , Haoyu Cui , Zhihao Yan , Yizhi Ding , Zhangrui Qian , Weiwei Shan

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

Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to deploy and fine-tune LLMs on mobile edge devices with…

Machine Learning · Computer Science 2023-11-23 Yuhao Chen , Yuxuan Yan , Qianqian Yang , Yuanchao Shu , Shibo He , Jiming Chen

Recent advances in Large Language Models (LLMs) have led to the widespread adoption of third-party inference services, raising critical privacy concerns. Existing methods of performing private third-party inference, such as Secure…

Cryptography and Security · Computer Science 2025-05-27 Rahul Thomas , Louai Zahran , Erica Choi , Akilesh Potti , Micah Goldblum , Arka Pal

Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…

Artificial Intelligence · Computer Science 2025-04-17 Hyungwoo Lee , Kihyun Kim , Jinwoo Kim , Jungmin So , Myung-Hoon Cha , Hong-Yeon Kim , James J. Kim , Youngjae Kim

Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their tight integration with non-deterministic models and…

Cryptography and Security · Computer Science 2026-05-07 Sina Abdollahi , Mohammad M Maheri , Javad Forough , Amir Al Sadi , Josh Millar , David Kotz , Marios Kogias , Hamed Haddadi

Edge computing enables real-time data processing closer to its source, thus improving the latency and performance of edge-enabled AI applications. However, traditional AI models often fall short when dealing with complex, dynamic tasks that…

Networking and Internet Architecture · Computer Science 2025-07-02 Haoxiang Luo , Yinqiu Liu , Ruichen Zhang , Jiacheng Wang , Gang Sun , Dusit Niyato , Hongfang Yu , Zehui Xiong , Xianbin Wang , Xuemin Shen

System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minimal latency to every request, yet not require a dedicated GPU…

Computation and Language · Computer Science 2026-03-16 Xunzhuo Liu , Bowei He , Xue Liu , Andy Luo , Haichen Zhang , Huamin Chen

Serving large language models (LLMs) for massive users is challenged by the significant memory footprint of the transient state, known as the key-value (KV) cache, which scales with sequence length and number of requests. Instead of renting…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-14 Liu Qianli , Hong Zicong , Chen Fahao , Li Peng , Guo Song

Quantum Federated Learning (QFL) enables distributed training of Quantum Machine Learning (QML) models by sharing model gradients instead of raw data. However, these gradients can still expose sensitive user information. To enhance privacy,…

Cryptography and Security · Computer Science 2026-03-04 Lukas Böhm , Arjhun Swaminathan , Anika Hannemann , Erik Buchmann

Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance on centralized providers. However, in a permissionless…

Cryptography and Security · Computer Science 2026-01-23 Ke Wang , Zishuo Zhao , Xinyuan Song , Zelin Li , Libin Xia , Chris Tong , Bill Shi , Wenjie Qu , Eric Yang , Lynn Ai

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

Key-Value (KV) cache quantization has become a widely adopted optimization technique for efficient large language models (LLMs) inference by reducing KV cache memory usage and mitigating memory-bound constraints. Recent studies have…

Computation and Language · Computer Science 2025-08-07 Zunhai Su , Kehong Yuan

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have…

Hardware Architecture · Computer Science 2026-01-29 Duo Chai , Zizhen Liu , Shuhuai Wang , Songwei Pei , Cheng Liu , Huawei Li , Shangguang Wang
‹ Prev 1 8 9 10 Next ›