English
Related papers

Related papers: BRDS: An FPGA-based LSTM Accelerator with Row-Bala…

200 papers

The need to recognise long-term dependencies in sequential data such as video streams has made Long Short-Term Memory (LSTM) networks a prominent Artificial Intelligence model for many emerging applications. However, the high computational…

Signal Processing · Electrical Eng. & Systems 2019-10-31 Alexandros Kouris , Stylianos I. Venieris , Michail Rizakis , Christos-Savvas Bouganis

We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,\mu$s using convolutional…

As its core computation, a self-attention mechanism gauges pairwise correlations across the entire input sequence. Despite favorable performance, calculating pairwise correlations is prohibitively costly. While recent work has shown the…

Machine Learning · Computer Science 2022-09-02 Amir Yazdanbakhsh , Ashkan Moradifirouzabadi , Zheng Li , Mingu Kang

Recurrent neural networks (RNNs) have been widely adopted in temporal sequence analysis, where realtime performance is often in demand. However, RNNs suffer from heavy computational workload as the model often comes with large weight…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-05-13 Runbin Shi , Peiyan Dong , Tong Geng , Yuhao Ding , Xiaolong Ma , Hayden K. -H. So , Martin Herbordt , Ang Li , Yanzhi Wang

Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their…

Machine Learning · Computer Science 2024-08-08 Mingyang Zhang , Hao Chen , Chunhua Shen , Zhen Yang , Linlin Ou , Xinyi Yu , Bohan Zhuang

The evolution of parallel I/O library as well as new concepts such as 'in transit' and 'in situ' visualization and analysis have been identified as key technologies to circumvent I/O bottleneck in pre-exascale applications. Nevertheless,…

Instrumentation and Methods for Astrophysics · Physics 2022-09-13 Loïc Strafella , Damien Chapon

Pruning is a widely used technique to compress large language models (LLMs) by removing unimportant weights, but it often suffers from significant performance degradation - especially under semi-structured sparsity constraints. Existing…

Machine Learning · Computer Science 2025-12-18 Tianteng Gu , Bei Liu , Bo Xiao , Ke Zeng , Jiacheng Liu , Yanmin Qian

Activation sparsity can reduce the computational overhead and memory transfers during the forward pass of Large Language Model (LLM) inference. Existing methods face limitations, either demanding time-consuming recovery training that…

Computation and Language · Computer Science 2026-01-06 Kai Liu , Bowen Xu , Shaoyu Wu , Xin Chen , Hao Zhou , Yongliang Tao , Lulu Hu

The deployment of large language models (LLMs) is often constrained by their substantial computational and memory demands. While structured pruning presents a viable approach by eliminating entire network components, existing methods suffer…

Machine Learning · Computer Science 2025-05-07 Hanyu Hu , Xiaoming Yuan

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with…

Computation and Language · Computer Science 2025-01-16 Yuxuan Hu , Jing Zhang , Xiaodong Chen , Zhe Zhao , Cuiping Li , Hong Chen

The recent rise of Large Language Models (LLMs) has revolutionized the deep learning field. However, the desire to deploy LLMs on edge devices introduces energy efficiency and latency challenges. Recurrent LLM (R-LLM) architectures have…

Neural and Evolutionary Computing · Computer Science 2025-01-29 Ivan Knunyants , Maryam Tavakol , Manolis Sifalakis , Yingfu Xu , Amirreza Yousefzadeh , Guangzhi Tang

Large Language Models (LLMs) present significant computational and memory challenges due to their extensive size, making pruning essential for their efficient deployment. Existing one-shot pruning methods often apply uniform sparsity…

Computation and Language · Computer Science 2025-10-14 Florentin Beck , William Rudman , Carsten Eickhoff

Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular…

Neural and Evolutionary Computing · Computer Science 2015-12-31 Sajid Anwar , Kyuyeon Hwang , Wonyong Sung

This paper presents Thanos, a novel weight-pruning algorithm designed to reduce the memory footprint and enhance the computational efficiency of large language models (LLMs) by removing redundant weights while maintaining accuracy. Thanos…

Machine Learning · Computer Science 2025-04-09 Ivan Ilin , Peter Richtarik

Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource…

Machine Learning · Computer Science 2024-02-12 Saleh Ashkboos , Maximilian L. Croci , Marcelo Gennari do Nascimento , Torsten Hoefler , James Hensman

State-space language models such as Mamba match Transformer quality while permitting linear complexity inference, yet still comprise billions of parameters that hinder deployment. Existing one-shot pruning methods are tailored to attention…

Machine Learning · Computer Science 2025-06-12 Kaiwen Tuo , Huan Wang

Simulated annealing (SA) is a well-known algorithm for solving combinatorial optimization problems. However, the computation time of SA increases rapidly, as the size of the problem grows. Recently, a stochastic simulated annealing (SSA)…

Hardware Architecture · Computer Science 2026-01-27 Duckgyu Shin , Naoya Onizawa , Warren J. Gross , Takahiro Hanyu

Despite the remarkable success of Large Language Models (LLMs), the massive size poses significant deployment challenges, particularly on resource-constrained hardware. While existing LLM compression methods focus on quantization, pruning…

Artificial Intelligence · Computer Science 2023-10-12 Song Guo , Jiahang Xu , Li Lyna Zhang , Mao Yang

Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism…

Machine Learning · Computer Science 2019-05-15 Dongsoo Lee , Se Jung Kwon , Byeongwook Kim , Parichay Kapoor , Gu-Yeon Wei

During the last years, algorithms known as Convolutional Neural Networks (CNNs) had become increasingly popular, expanding its application range to several areas. In particular, the image processing field has experienced a remarkable…

Hardware Architecture · Computer Science 2024-08-27 Federico Nicolas Peccia , Luciano Ferreyro , Alejandro Furfaro