English
Related papers

Related papers: A Tensor-Train Decomposition based Compression of …

200 papers

Small Language Models (SLMs, or on-device LMs) have significantly fewer parameters than Large Language Models (LLMs). They are typically deployed on low-end devices, like mobile phones and single-board computers. Unlike LLMs, which rely on…

Computation and Language · Computer Science 2025-06-17 Mingxue Xu , Yao Lei Xu , Danilo P. Mandic

The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large, the corresponding weight matrices can be enormous,…

Computation and Language · Computer Science 2020-02-20 Oleksii Hrinchuk , Valentin Khrulkov , Leyla Mirvakhabova , Elena Orlova , Ivan Oseledets

High-dimensional token embeddings underpin Large Language Models (LLMs), as they can capture subtle semantic information and significantly enhance the modelling of complex language patterns. However, this high dimensionality also introduces…

Computation and Language · Computer Science 2024-10-07 Mingxue Xu , Yao Lei Xu , Danilo P. Mandic

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing (NLP) tasks, such as question-answering, sentiment analysis, text summarization, and machine…

Machine Learning · Computer Science 2024-08-05 Afia Anjum , Maksim E. Eren , Ismael Boureima , Boian Alexandrov , Manish Bhattarai

The growing demands of distributed learning on resource constrained edge devices underscore the importance of efficient on device model compression. Tensor Train Decomposition (TTD) offers high compression ratios with minimal accuracy loss,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-19 Hyunseok Kwak , Kyeongwon Lee , Kyeongpil Min , Chaebin Jung , Woojoo Lee

Since Large Language Models or LLMs have demonstrated high-quality performance on many complex language tasks, there is a great interest in bringing these LLMs to mobile devices for faster responses and better privacy protection. However,…

Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators…

Machine Learning · Computer Science 2026-01-07 Jan Hansen-Palmus , Michael Truong Le , Oliver Hausdörfer , Alok Verma

The prevalent fully-connected tensor network (FCTN) has achieved excellent success to compress data. However, the FCTN decomposition suffers from slow computational speed when facing higher-order and large-scale data. Naturally, there…

Machine Learning · Computer Science 2022-10-20 Peilin Yang , Weijun Sun , Qibin Zhao , Guoxu Zhou

Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities as their scale expands to billions of parameters. Deploying these large-scale models on resource-constrained platforms presents significant…

Hardware Architecture · Computer Science 2025-05-15 Keran Zheng , Yinting Huang , Zhewen Yu , Christos-Savvas Bouganis

The memory capacity of embedding tables in deep learning recommendation models (DLRMs) is increasing dramatically from tens of GBs to TBs across the industry. Given the fast growth in DLRMs, novel solutions are urgently needed, in order to…

Machine Learning · Computer Science 2021-01-29 Chunxing Yin , Bilge Acun , Xing Liu , Carole-Jean Wu

Large language models (LLMs) have demonstrated remarkable abilities in natural language processing. However, their deployment on resource-constrained embedded devices remains difficult due to memory and computational demands. In this paper,…

Hardware Architecture · Computer Science 2024-09-19 Han Xu , Yutong Li , Shihao Ji

During the training of Large Language Models (LLMs), tensor data is periodically "checkpointed" to persistent storage to allow recovery of work done in the event of failure. The volume of data that must be copied during each checkpoint,…

Machine Learning · Computer Science 2025-05-16 Daniel Waddington , Cornel Constantinescu

Hardware accelerators, in particular accelerators for tensor processing, have many potential application domains. However, they currently lack the software infrastructure to support the majority of domains outside of deep learning.…

Hardware Architecture · Computer Science 2024-08-08 Charles Hong , Sahil Bhatia , Altan Haan , Shengjun Kris Dong , Dima Nikiforov , Alvin Cheung , Yakun Sophia Shao

The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for…

Computation and Language · Computer Science 2025-10-14 Ryan Solgi , Kai Zhen , Rupak Vignesh Swaminathan , Nathan Susanj , Athanasios Mouchtaris , Siegfried Kunzmann , Zheng Zhang

To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core…

Hardware Architecture · Computer Science 2025-08-11 Gerasimos Gerogiannis , Stijn Eyerman , Evangelos Georganas , Wim Heirman , Josep Torrellas

The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to…

Hardware Architecture · Computer Science 2026-03-24 Zifan He , Shengyu Ye , Rui Ma , Yang Wang , Jason Cong

The increase in open-source availability of Large Language Models (LLMs) has enabled users to deploy them on more and more resource-constrained edge devices to reduce reliance on network connections and provide more privacy. However, the…

Hardware Architecture · Computer Science 2024-08-02 Jude Haris , Rappy Saha , Wenhao Hu , José Cano

Low Rank Decomposition of matrix - splitting a large matrix into a product of two smaller matrix offers a means for compression that reduces the parameters of a model without sparsification, and hence delivering more speedup on modern…

Computation and Language · Computer Science 2023-09-26 Ayush Kaushal , Tejas Vaidhya , Irina Rish

Current LLM structured pruning methods typically involve two steps: (1) compression with calibration data and (2) costly continued pretraining on billions of tokens to recover lost performance. This second step is necessary as the first…

Machine Learning · Computer Science 2024-12-31 Yaya Sy , Christophe Cerisara , Irina Illina

The extremely high computational and storage demands of large language models have excluded most edge devices, which were widely used for efficient machine learning, from being viable options. A typical edge device usually only has 4GB of…

Hardware Architecture · Computer Science 2025-02-18 Jindong Li , Tenglong Li , Guobin Shen , Dongcheng Zhao , Qian Zhang , Yi Zeng
‹ Prev 1 2 3 10 Next ›