English
Related papers

Related papers: FullPack: Full Vector Utilization for Sub-Byte Qua…

200 papers

Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e.,…

Hardware Architecture · Computer Science 2025-07-23 Jan Klhufek , Miroslav Safar , Vojtech Mrazek , Zdenek Vasicek , Lukas Sekanina

Retrieval-Augmented Generation enhances language models by retrieving relevant information from external knowledge bases, relying on high-dimensional vector embeddings typically stored in float32 precision. However, storing these embeddings…

Transformer models have achieved remarkable success across various AI applications but face significant training costs. Low-bit training, such as INT8 training, can leverage computational units with higher throughput, and has already…

Machine Learning · Computer Science 2025-06-10 Pengle Zhang , Jia Wei , Jintao Zhang , Jun Zhu , Jianfei Chen

Large Language Models (LLMs) have achieved state-of-the-art performance across various language tasks but pose challenges for practical deployment due to their substantial memory requirements. Furthermore, the latest generative models…

Machine Learning · Computer Science 2023-08-22 Young Jin Kim , Rawn Henry , Raffy Fahim , Hany Hassan Awadalla

The optimizations of both memory depth and kernel functions are critical for wideband digital pre-distortion (DPD). However, the memory depth is usually determined via exhaustive search over a wide range for the sake of linearization…

Signal Processing · Electrical Eng. & Systems 2025-04-21 Jinfei Wang , Yi Ma , Fei Tong , Ziming He

CPU-based inference can be an alternative to off-chip accelerators, and vector architectures are a promising option due to their efficiency. However, the large design space of convolutional algorithms and hardware implementations makes it…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-12-23 Sonia Rani Gupta , Nikela Papadopoulou , Miquel Pericas

Deep neural networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. A common approach to implementing DNNs is to recast the most computationally expensive operations as…

Computer Vision and Pattern Recognition · Computer Science 2017-09-12 Andrew Anderson , Aravind Vasudevan , Cormac Keane , David Gregg

Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their extensive output vocabularies. The final linear projection layer, mapping hidden states to…

Computation and Language · Computer Science 2025-05-16 Jintian Shao , Hongyi Huang , Jiayi Wu , YiMing Cheng , ZhiYu Wu , You Shan , MingKai Zheng

Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed…

Machine Learning · Computer Science 2025-11-18 Vladimír Macko , Vladimír Boža

Binary Neural Networks (BNNs) are showing tremendous success on realistic image classification tasks. Notably, their accuracy is similar to the state-of-the-art accuracy obtained by full-precision models tailored to edge devices. In this…

Hardware Architecture · Computer Science 2022-12-02 Franyell Silfa , Jose Maria Arnau , Antonio González

Video large language models (VideoLLMs) have demonstrated the capability to process longer video inputs and enable complex reasoning and analysis. However, due to the thousands of visual tokens from the video frames, the key-value (KV)…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Keda Tao , Haoxuan You , Yang Sui , Can Qin , Huan Wang

Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield significant performance and energy improvements…

Hardware Architecture · Computer Science 2022-04-05 Christina Giannoula , Ivan Fernandez , Juan Gómez-Luna , Nectarios Koziris , Georgios Goumas , Onur Mutlu

FPGAs are a promising platform for accelerating Deep Learning (DL) applications, due to their high performance, low power consumption, and reconfigurability. Recently, the leading FPGA vendors have enhanced their architectures to more…

Hardware Architecture · Computer Science 2024-04-18 Endri Taka , Dimitrios Gourounas , Andreas Gerstlauer , Diana Marculescu , Aman Arora

Large language models (LLMs) have transformed the way we think about language understanding and generation, enthralling both researchers and developers. However, deploying LLMs for inference has been a significant challenge due to their…

Machine Learning · Computer Science 2025-01-03 Dibakar Gope , David Mansell , Danny Loh , Ian Bratt

We propose a novel 2-stage sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. For the 1st-stage, we adapt a recently proposed quantization…

In deep learning frameworks, weight pruning is a widely used technique for improving computational efficiency by reducing the size of large models. This is especially critical for convolutional operators, which often act as performance…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-24 Chi-Wei Chu , Ding-Yong Hong , Jan-Jan Wu

Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield significant performance and energy improvements…

Hardware Architecture · Computer Science 2022-05-24 Christina Giannoula , Ivan Fernandez , Juan Gómez-Luna , Nectarios Koziris , Georgios Goumas , Onur Mutlu

Processing-in-memory (PIM) architectures are emerging to reduce data movement in data-intensive applications. These architectures seek to exploit the same physical devices for both information storage and logic, thereby dwarfing the…

Hardware Architecture · Computer Science 2023-05-09 Orian Leitersdorf , Ronny Ronen , Shahar Kvatinsky

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued,…

Computation and Language · Computer Science 2019-06-21 Dinghan Shen , Pengyu Cheng , Dhanasekar Sundararaman , Xinyuan Zhang , Qian Yang , Meng Tang , Asli Celikyilmaz , Lawrence Carin

Kernel methods are a highly effective and widely used collection of modern machine learning algorithms. A fundamental limitation of virtually all such methods are computations involving the kernel matrix that naively scale quadratically…

Machine Learning · Computer Science 2021-06-09 John Paul Ryan , Sebastian Ament , Carla P. Gomes , Anil Damle