English
Related papers

Related papers: Privacy-Aware Split Inference with Speculative Dec…

200 papers

Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Yicheng Ji , Jun Zhang , Heming Xia , Jinpeng Chen , Lidan Shou , Gang Chen , Huan Li

To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have…

Machine Learning · Computer Science 2025-08-19 Jihoon Park , Seungeun Oh , Seong-Lyun Kim

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary challenges are memory…

Hardware Architecture · Computer Science 2026-02-10 Xiaoyu Ma , David Patterson

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95% of their original top-1 prediction accuracy without any…

Machine Learning · Computer Science 2025-06-17 Vedang Lad , Jin Hwa Lee , Wes Gurnee , Max Tegmark

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…

Machine Learning · Computer Science 2019-06-07 Alon Brutzkus , Oren Elisha , Ran Gilad-Bachrach

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms…

Computation and Language · Computer Science 2024-12-03 Ruslan Svirschevski , Avner May , Zhuoming Chen , Beidi Chen , Zhihao Jia , Max Ryabinin

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Computation and Language · Computer Science 2025-05-14 Danying Ge , Jianhua Gao , Qizhi Jiang , Yifei Feng , Weixing Ji

Large language models (LLMs) have transformed natural language processing but face critical deployment challenges in device-edge systems due to resource limitations and communication overhead. To address these issues, collaborative…

Signal Processing · Electrical Eng. & Systems 2025-07-18 Jiahong Ning , Ce Zheng , Tingting Yang

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

Cryptography and Security · Computer Science 2025-05-05 Wenjie Qu , Yuguang Zhou , Yongji Wu , Tingsong Xiao , Binhang Yuan , Yiming Li , Jiaheng Zhang

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Computation and Language · Computer Science 2025-02-11 Jun Zhang , Jue Wang , Huan Li , Lidan Shou , Ke Chen , Gang Chen , Sharad Mehrotra

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer…

Machine Learning · Computer Science 2024-10-08 Lijie Yang , Zhihao Zhang , Zhuofu Chen , Zikun Li , Zhihao Jia

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not…

Machine Learning · Computer Science 2024-12-20 Lanxiang Hu , Tajana Rosing , Hao Zhang

A systematic understanding of Apple Silicon is lacking in the current landscape of hardware efficiency; research focus is largely centered on accelerating GPUs for large-scale training or inference on CUDA devices. This paper investigates…

Performance · Computer Science 2025-08-13 Afsara Benazir , Felix Xiaozhu Lin

Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As these models grow more capable, it is crucial to enable…

Artificial Intelligence · Computer Science 2024-04-19 Stefan Dernbach , Khushbu Agarwal , Alejandro Zuniga , Michael Henry , Sutanay Choudhury

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…

Cryptography and Security · Computer Science 2026-04-21 Noor Islam S. Mohammad , Uluğ Bayazıt

The rapid advancement of Large Language Models (LLMs) necessitates a deep understanding of their fundamental performance limits. This paper investigates the limits of LLM inference, focusing on hardware-imposed bottlenecks in…

Hardware Architecture · Computer Science 2025-11-17 Michael Davies , Neal Crago , Karthikeyan Sankaralingam , Christos Kozyrakis

Speculative Decoding is a widely used technique to speed up inference for Large Language Models (LLMs) without sacrificing quality. When performing inference, speculative decoding uses a smaller draft model to generate speculative tokens…

Machine Learning · Computer Science 2025-02-06 Minghao Yan , Saurabh Agarwal , Shivaram Venkataraman

Split learning (SL) enables data privacy preservation by allowing clients to collaboratively train a deep learning model with the server without sharing raw data. However, SL still has limitations such as potential data privacy leakage and…

Machine Learning · Computer Science 2022-06-13 Ngoc Duy Pham , Alsharif Abuadbba , Yansong Gao , Tran Khoa Phan , Naveen Chilamkurti

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

Machine Learning · Computer Science 2025-10-08 Hanbo Huang , Yihan Li , Bowen Jiang , Bo Jiang , Lin Liu , Ruoyu Sun , Zhuotao Liu , Shiyu Liang

Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients'…

Machine Learning · Computer Science 2025-01-22 Haonan Shi , Tu Ouyang , An Wang