English
Related papers

Related papers: SLaNC: Static LayerNorm Calibration

200 papers

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-06 Xiangchen Li , Dimitrios Spatharakis , Saeid Ghafouri , Jiakun Fan , Hans Vandierendonck , Deepu John , Bo Ji , Dimitrios Nikolopoulos

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Machine Learning · Computer Science 2024-07-26 Yao Fu , Leyang Xue , Yeqi Huang , Andrei-Octavian Brabete , Dmitrii Ustiugov , Yuvraj Patel , Luo Mai

Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters and reliance on dense multiplications, resulting in high…

Machine Learning · Computer Science 2024-11-20 Haoran You , Yipin Guo , Yichao Fu , Wei Zhou , Huihong Shi , Xiaofan Zhang , Souvik Kundu , Amir Yazdanbakhsh , Yingyan Celine Lin

Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy. However, challenges such as high computational and memory demands, heterogeneous client…

Machine Learning · Computer Science 2025-05-19 Yang Su , Na Yan , Yansha Deng , Mischa Dohler , Robert Schober

Neural networks have become dominant computational workloads across cloud and edge platforms, but their rapid growth in model size and deployment diversity has exposed hardware bottlenecks increasingly dominated by memory movement,…

Systems and Control · Electrical Eng. & Systems 2026-01-16 Bin Xu , Ayan Banerjee , Sandeep Gupta

Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…

Hardware Architecture · Computer Science 2025-07-15 Chun-Ting Chen , HanGyeol Mun , Jian Meng , Mohamed S. Abdelfattah , Jae-sun Seo

The recently proposed Conformer architecture which combines convolution with attention to capture both local and global dependencies has become the \textit{de facto} backbone model for Automatic Speech Recognition~(ASR). Inherited from the…

Large language model (LLM) inference poses significant challenges due to its intensive memory and computation demands. Weight and activation quantization (WAQ) offers a promising solution by reducing both memory footprint and arithmetic…

Machine Learning · Computer Science 2025-09-11 Xueying Wu , Baijun Zhou , Zhihui Gao , Yuzhe Fu , Qilin Zheng , Yintao He , Hai Li

Quantization is the key method for reducing inference latency, power and memory footprint of generative AI models. However, accuracy often degrades sharply when activations are quantized below eight bits. Recent work suggests that…

Machine Learning · Computer Science 2025-10-31 Marco Federici , Riccardo Del Chiaro , Boris van Breugel , Paul Whatmough , Markus Nagel

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-03 Junseok Lee , Sangyong Lee , Chang-Jae Chun

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Ruihan Lin , Zezhen Ding , Zean Han , Jiheng Zhang

Large language models (LLMs) are increasingly used across research and industry applications, yet their inference efficiency remains a significant challenge. As the computational power of modern GPU architectures continuously improves,…

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-08 Kunal Jain , Anjaly Parayil , Ankur Mallick , Esha Choukse , Xiaoting Qin , Jue Zhang , Íñigo Goiri , Rujia Wang , Chetan Bansal , Victor Rühle , Anoop Kulkarni , Steve Kofsky , Saravan Rajmohan

This paper addresses the challenge of large model (LM)-embedded wireless network for handling the trade-off problem of model accuracy and network latency. To guarantee a high-quality of users' service, the network latency should be…

Signal Processing · Electrical Eng. & Systems 2025-08-05 Yichen Jin , Zongze Li , Zeyi Ren , Qingfeng Lin , Yik-Chung Wu

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity hardware like a single GPU. Due to the memory and power…

Computation and Language · Computer Science 2024-01-09 Zirui Liu , Qingquan Song , Qiang Charles Xiao , Sathiya Keerthi Selvaraj , Rahul Mazumder , Aman Gupta , Xia Hu

In a world burdened by air pollution, the integration of state-of-the-art sensor calibration techniques utilizing Quantum Computing (QC) and Machine Learning (ML) holds promise for enhancing the accuracy and efficiency of air quality…

Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to reduce LLM inference cost by reducing latency and memory…

Machine Learning · Computer Science 2024-11-12 Jinhao Li , Jiaming Xu , Shiyao Li , Shan Huang , Jun Liu , Yaoxiu Lian , Guohao Dai

Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…

Artificial Intelligence · Computer Science 2025-10-29 Chengwei Wu , Li Du , Hanyu Zhao , Yiming Ju , Jiapu Wang , Tianyu Chen , Haoyi Zhou

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…

Operating Systems · Computer Science 2025-03-07 Hongchao Du , Shangyu Wu , Arina Kharlamova , Nan Guan , Chun Jason Xue

Predicates are foundational components in data analysis systems. However, modern workloads increasingly involve unstructured documents, which demands semantic understanding, beyond traditional value-based predicates. Given enormous…

Databases · Computer Science 2026-05-22 Hengrui Zhang , Yulong Hui , Yihao Liu , Huanchen Zhang