Low-Bit Integerization of Vision Transformers using Operand Reodering for Efficient Hardware

• URL: http://arxiv.org/abs/2504.18547v1
• Date: Fri, 11 Apr 2025 16:09:54 GMT
• Title: Low-Bit Integerization of Vision Transformers using Operand Reodering for Efficient Hardware
• Authors: Ching-Yi Lin, Sahil Shah,
• Abstract summary: We analyze the computation graph and propose an integerization process based on operation reordering.<n>This enables integerized matrix multiplication and linear module by directly processing the quantized input.<n> Experimental results show that our low-bit inference reduces per-PE power consumption for linear layer and matrix multiplication.
• Score: 0.7136205674624813
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Pre-trained vision transformers have achieved remarkable performance across various visual tasks but suffer from expensive computational and memory costs. While model quantization reduces memory usage by lowering precision, these models still incur significant computational overhead due to the dequantization before matrix operations. In this work, we analyze the computation graph and propose an integerization process based on operation reordering. Specifically, the process delays dequantization until after matrix operations. This enables integerized matrix multiplication and linear module by directly processing the quantized input. To validate our approach, we synthesize the self-attention module of ViT on a systolic array-based hardware. Experimental results show that our low-bit inference reduces per-PE power consumption for linear layer and matrix multiplication, bridging the gap between quantized models and efficient inference.

Related papers

• Orthogonal Finetuning Made Scalable [87.49040247077389]
  Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment.<n>We identify the core computational bottleneck in OFT as its weight-centric implementation, which relies on costly matrix-matrix multiplications with cubic complexity.<n>We propose OFTv2, an input-centric reformulation that instead uses matrix-vector multiplications (i.e., matrix-free computation), reducing the computational cost to quadratic.<n>These modifications allow OFTv2 to achieve up to 10x faster training and 3x lower GPU memory usage without compromising performance.
  arXiv  Detail & Related papers  (2025-06-24T17:59:49Z)
• Scaling Probabilistic Circuits via Monarch Matrices [109.65822339230853]
  Probabilistic Circuits (PCs) are tractable representations of probability distributions.<n>We propose a novel sparse and structured parameterization for the sum blocks in PCs.
  arXiv  Detail & Related papers  (2025-06-14T07:39:15Z)
• LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers [79.07412045476872]
  Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks.<n>We show that performing the full of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps.<n>We propose a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations.
  arXiv  Detail & Related papers  (2024-12-17T01:12:35Z)
• MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers [43.39466934693055]
  We present MemoryFormer, a novel transformer architecture which significantly reduces the computational complexity (FLOPs) from a new perspective. This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers. We conduct extensive experiments on various benchmarks to demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2024-11-20T02:41:53Z)
• An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks [8.779871128906787]
  We propose algorithms to improve the inference time and memory efficiency of Deep Neural Networks (DNNs)<n>We focus on matrix multiplication as the bottleneck operation of inference.<n>Our experiments show up to a 5.24x speedup in the inference time.
  arXiv  Detail & Related papers  (2024-11-10T04:56:14Z)
• Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores [3.6385567224218556]
  Large language models (LLMs) have been widely applied but face challenges in efficient inference. We introduce a novel bipolar-INT data format that facilitates parallel computing and supports symmetric quantization. We implement an arbitrary precision matrix multiplication scheme that decomposes and recovers at the bit level, enabling flexible precision.
  arXiv  Detail & Related papers  (2024-09-26T14:17:58Z)
• Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization [0.6445087473595953]
  Large language models (LLMs) demonstrate outstanding performance in various tasks in machine learning. deploying LLM inference poses challenges due to the high compute and memory requirements. We present Tender, an algorithm-hardware co-design solution that enables efficient deployment of LLM inference at low precision.
  arXiv  Detail & Related papers  (2024-06-16T09:51:55Z)
• DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention [53.02648818164273]
  We present an efficient yet effective attention mechanism, namely the Dynamic Bilinear Low-Rank Attention (DBA) DBA compresses the sequence length by input-sensitive dynamic projection matrices and achieves linear time and space complexity. Experiments over tasks with diverse sequence length conditions show that DBA achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-11-24T03:06:36Z)
• Softmax-free Linear Transformers [90.83157268265654]
  Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. Existing methods are either theoretically flawed or empirically ineffective for visual recognition. We propose a family of Softmax-Free Transformers (SOFT)
  arXiv  Detail & Related papers  (2022-07-05T03:08:27Z)
• Memory-Efficient Backpropagation through Large Linear Layers [107.20037639738433]
  In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers.
  arXiv  Detail & Related papers  (2022-01-31T13:02:41Z)
• Mesa: A Memory-saving Training Framework for Transformers [58.78933015299703]
  We present Mesa, a memory-saving training framework for Transformers. Mesa uses exact activations during forward pass while storing a low-precision version of activations to reduce memory consumption during training. Experiments on ImageNet, CIFAR-100 and ADE20K demonstrate that Mesa can reduce half of the memory footprints during training.
  arXiv  Detail & Related papers  (2021-11-22T11:23:01Z)
• Post-Training Quantization for Vision Transformer [85.57953732941101]
  We present an effective post-training quantization algorithm for reducing the memory storage and computational costs of vision transformers. We can obtain an 81.29% top-1 accuracy using DeiT-B model on ImageNet dataset with about 8-bit quantization.
  arXiv  Detail & Related papers  (2021-06-27T06:27:22Z)
• Accelerating Neural Network Inference by Overflow Aware Quantization [16.673051600608535]
  Inherited heavy computation of deep neural networks prevents their widespread applications. We propose an overflow aware quantization method by designing trainable adaptive fixed-point representation. With the proposed method, we are able to fully utilize the computing power to minimize the quantization loss and obtain optimized inference performance.
  arXiv  Detail & Related papers  (2020-05-27T11:56:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.