English
Related papers

Related papers: Supporting Massive DLRM Inference Through Software…

200 papers

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…

Deep Learning Recommendation Models (DLRMs) have gained popularity in recommendation systems due to their effectiveness in handling large-scale recommendation tasks. The embedding layers of DLRMs have become the performance bottleneck due…

Information Retrieval · Computer Science 2024-10-10 Sitian Chen , Haobin Tan , Amelie Chi Zhou , Yusen Li , Pavan Balaji

Deep Learning Recommendation Models (DLRMs) play a crucial role in delivering personalized content across web applications such as social networking and video streaming. However, with improvements in performance, the parameter size of DLRMs…

Hardware Architecture · Computer Science 2025-04-02 Jinho Yang , Ji-Hoon Kim , Joo-Young Kim

Deep Recommender Models (DLRMs) inference is a fundamental AI workload accounting for more than 79% of the total AI workload in Meta's data centers. DLRMs' performance bottleneck is found in the embedding layers, which perform many random…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-03 Giuseppe Ruggeri , Renzo Andri , Daniele Jahier Pagliari , Lukas Cavigelli

Deep learning recommendation models (DLRM) rely on large embedding tables to manage categorical sparse features. Expanding such embedding tables can significantly enhance model performance, but at the cost of increased GPU/CPU/memory usage.…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-01 Qinlong Wang , Tingfeng Lan , Yinghao Tang , Ziling Huang , Yiheng Du , Haitao Zhang , Jian Sha , Hui Lu , Yuanchun Zhou , Ke Zhang , Mingjie Tang

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage…

Information Retrieval · Computer Science 2022-08-11 Jiarui Fang , Geng Zhang , Jiatong Han , Shenggui Li , Zhengda Bian , Yongbin Li , Jin Liu , Yang You

The energy consumed by running large deep neural networks (DNNs) on hardware accelerators is dominated by the need for lots of fast memory to store both states and weights. This large required memory is currently only economically viable…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Tobi Delbruck , Shih-Chii Liu

Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving,…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-13 Michael Lui , Yavuz Yetim , Özgür Özkan , Zhuoran Zhao , Shin-Yeh Tsai , Carole-Jean Wu , Mark Hempstead

Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value representations for past tokens, whose size scales linearly with the…

Computation and Language · Computer Science 2024-07-24 Piotr Nawrot , Adrian Łańcucki , Marcin Chochowski , David Tarjan , Edoardo M. Ponti

With emerging storage-class memory (SCM) nearing commercialization, there is evidence that it will deliver the much-anticipated high density and access latencies within only a few factors of DRAM. Nevertheless, the latency-sensitive nature…

Embedding tables dominate industrial-scale recommendation model sizes, using up to terabytes of memory. A popular and the largest publicly available machine learning MLPerf benchmark on recommendation data is a Deep Learning Recommendation…

Machine Learning · Computer Science 2022-07-25 Aditya Desai , Anshumali Shrivastava

Storage-class memory (SCM) combines the benefits of a solid-state memory, such as high-performance and robustness, with the archival capabilities and low cost of conventional hard-disk magnetic storage. Among candidate solid-state…

Hardware Architecture · Computer Science 2017-04-19 Wonil Choi , Mohammad Arjomand , Myoungsoo Jung , Mahmut Kandemir

Personalized recommendation is a ubiquitous application on the internet, with many industries and hyperscalers extensively leveraging Deep Learning Recommendation Models (DLRMs) for their personalization needs (like ad serving or movie…

Hardware Architecture · Computer Science 2024-10-30 Rishabh Jain , Vivek M. Bhasi , Adwait Jog , Anand Sivasubramaniam , Mahmut T. Kandemir , Chita R. Das

While containers efficiently implement the idea of operating-system-level application virtualization, they are often insufficient to increase the server utilization to a desirable level. The reason is that in practice many containerized…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-06-26 Jan S. Rellermeyer , Maher Amer , Richard Smutzer , Karthick Rajamani

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

Hardware Architecture · Computer Science 2026-04-29 Mingbo Hao , Changwei Yan , Haoyu Cui , Zhihao Yan , Yizhi Ding , Zhangrui Qian , Weiwei Shan

Large Deep Neural Networks (DNNs) are the backbone of today's artificial intelligence due to their ability to make accurate predictions when being trained on huge datasets. With advancing technologies, such as the Internet of Things,…

Machine Learning · Computer Science 2023-07-14 Mark Deutel , Philipp Woller , Christopher Mutschler , Jürgen Teich

The use of low numerical precision is a fundamental optimization included in modern accelerators for Deep Neural Networks (DNNs). The number of bits of the numerical representation is set to the minimum precision that is able to retain…

Signal Processing · Electrical Eng. & Systems 2019-11-12 Franyell Silfa , Jose-Maria Arnau , Antonio Gonzàlez

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

Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the…

Machine Learning · Computer Science 2025-09-30 Yunchu Han , Zhaojun Nan , Sheng Zhou , Zhisheng Niu

Deep Learning is a very powerful machine learning model. Deep Learning trains a large number of parameters for multiple layers and is very slow when data is in large scale and the architecture size is large. Inspired from the shrinking…

Machine Learning · Computer Science 2016-09-20 Shuai Zheng , Abhinav Vishnu , Chris Ding
‹ Prev 1 2 3 10 Next ›