English
Related papers

Related papers: Enabling Dynamic Sparsity in Quantized LLM Inferen…

200 papers

Fine-tuning large language models (LLMs) requires significant memory, often exceeding the capacity of a single GPU. A common solution to this memory challenge is offloading compute and data from the GPU to the CPU. However, this approach is…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-11 Siyuan Chen , Zhuofeng Wang , Zelong Guan , Yudong Liu , Phillip B. Gibbons

Large Language Models (LLMs) offer strong capabilities but incur high inference costs due to dense computation and memory access. Training-free activation sparsity is a promising approach for efficient LLM inference, yet existing methods…

Machine Learning · Computer Science 2026-02-17 Lei Chen , Yuan Meng , Xiaoyu Zhan , Zhi Wang , Wenwu Zhu

While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-training from scratch. Recent studies have investigated the…

Machine Learning · Computer Science 2025-08-05 Jiaxi Li , Lu Yin , Li Shen , Jinjin Xu , Liwu Xu , Tianjin Huang , Wenwu Wang , Shiwei Liu , Xilu Wang

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

The computational demands of modern Deep Neural Networks (DNNs) are immense and constantly growing. While training costs usually capture public attention, inference demands are also contributing in significant computational, energy and…

Traditional pruning methods are known to be challenging to work in Large Language Models (LLMs) for Generative AI because of their unaffordable training process and large computational demands. For the first time, we introduce the…

Machine Learning · Computer Science 2024-03-25 Yun Li , Lin Niu , Xipeng Zhang , Kai Liu , Jianchen Zhu , Zhanhui Kang

In this paper, we present a novel method that reduces model inference latency during distributed deployment of Large Language Models (LLMs). Our contribution is an optimized inference deployment scheme that address the current limitations…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-08 Adnan Hoque , Mudhakar Srivatsa , Chih-Chieh Yang , Raghu Ganti

Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and memory accesses required for LLM training makes them…

Machine Learning · Computer Science 2023-03-10 Guo Yang , Daniel Lo , Robert Mullins , Yiren Zhao

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…

Hardware Architecture · Computer Science 2025-04-23 Rui Xie , Asad Ul Haq , Linsen Ma , Yunhua Fang , Zirak Burzin Engineer , Liu Liu , Tong Zhang

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance…

Computation and Language · Computer Science 2026-03-17 Dilxat Muhtar , Xinyuan Song , Sebastian Pokutta , Max Zimmer , Nico Pelleriti , Thomas Hofmann , Shiwei Liu

Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. In contrast, supporting multiple N:M patterns to provide sparse…

Machine Learning · Computer Science 2025-04-22 Akshat Ramachandran , Souvik Kundu , Arnab Raha , Shamik Kundu , Deepak K. Mathaikutty , Tushar Krishna

The sparse representation of graphs has shown great potential for accelerating the computation of graph applications (e.g., Social Networks, Knowledge Graphs) on traditional computing architectures (CPU, GPU, or TPU). But the exploration of…

Machine Learning · Computer Science 2024-10-28 Bo Lyu , Shengbo Wang , Shiping Wen , Kaibo Shi , Yin Yang , Lingfang Zeng , Tingwen Huang

Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Gautom Das , Vincent La , Ethan Lau , Abhinav Shrivastava , Matthew Gwilliam

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Machine Learning · Computer Science 2025-11-10 Adrian Łańcucki , Konrad Staniszewski , Piotr Nawrot , Edoardo M. Ponti

The billion-scale Large Language Models (LLMs) need deployment on expensive server-grade GPUs with large-storage HBMs and abundant computation capability. As LLM-assisted services become popular, achieving cost-effective LLM inference on…

Hardware Architecture · Computer Science 2025-02-25 Lian Liu , Shixin Zhao , Bing Li , Haimeng Ren , Zhaohui Xu , Mengdi Wang , Xiaowei Li , Yinhe Han , Ying Wang

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…

Machine Learning · Computer Science 2024-12-10 Weizhuo Li , Zhigang Wang , Yu Gu , Ge Yu

Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs.…

Neural and Evolutionary Computing · Computer Science 2026-04-22 Rachmad Vidya Wicaksana Putra , Pasindu Wickramasinghe , Muhammad Shafique

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

Machine Learning · Computer Science 2026-04-06 Xiangbo Qi , Chaoyi Jiang , Murali Annavaram

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

Machine Learning · Computer Science 2026-05-29 Wenhao Dai , Haodong Deng , Mengfei Rong , Xinyu Yang , Hongyu Liu , Fangxin Liu , Hailong Yang , Qianwen Cao , Qingxiao Sun