MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization

• URL: http://arxiv.org/abs/2412.10261v2
• Date: Mon, 16 Dec 2024 08:54:43 GMT
• Title: MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization
• Authors: Shuaiting Li, Chengxuan Wang, Juncan Deng, Zeyu Wang, Zewen Ye, Zongsheng Wang, Haibin Shen, Kejie Huang,
• Abstract summary: A novel approach called MVQ is proposed, which aims at better approximating important weights with a limited number of codewords. Our algorithm is validated on various models for image classification, object detection, and segmentation tasks. Under ASIC evaluation, our MVQ accelerator boosts energy efficiency by 2.3$times$ and reduces the size of the systolic array by 55% when compared with the base EWS accelerator.
• Score: 8.057807176915896
• License:
• Abstract: Vector quantization(VQ) is a hardware-friendly DNN compression method that can reduce the storage cost and weight-loading datawidth of hardware accelerators. However, conventional VQ techniques lead to significant accuracy loss because the important weights are not well preserved. To tackle this problem, a novel approach called MVQ is proposed, which aims at better approximating important weights with a limited number of codewords. At the algorithm level, our approach removes the less important weights through N:M pruning and then minimizes the vector clustering error between the remaining weights and codewords by the masked k-means algorithm. Only distances between the unpruned weights and the codewords are computed, which are then used to update the codewords. At the architecture level, our accelerator implements vector quantization on an EWS (Enhanced weight stationary) CNN accelerator and proposes a sparse systolic array design to maximize the benefits brought by masked vector quantization.\\ Our algorithm is validated on various models for image classification, object detection, and segmentation tasks. Experimental results demonstrate that MVQ not only outperforms conventional vector quantization methods at comparable compression ratios but also reduces FLOPs. Under ASIC evaluation, our MVQ accelerator boosts energy efficiency by 2.3$\times$ and reduces the size of the systolic array by 55\% when compared with the base EWS accelerator. Compared to the previous sparse accelerators, MVQ achieves 1.73$\times$ higher energy efficiency.

Related papers

• Pyramid Vector Quantization for LLMs [8.779688608449902]
  Pyramid Vector Quantization (PVQ) for large language models. PVQ uses a fixed integer lattice on the sphere by projecting points onto the 1-sphere, which allows for efficient encoding and decoding without requiring an explicit codebook in memory. We achieve state-of-the-art quantization performance with pareto-optimal trade-off between performance and bits per weight and bits per activation, compared to compared methods.
  arXiv  Detail & Related papers  (2024-10-22T11:57:32Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering [5.363038867793461]
  We formulate the Quantization Error Minimization problem as minimizing the distance between a matrix before and after quantization. Matrix quantization is crucial in various applications, including Large Language Models (LLMs) weight quantization, vector databases, KV cache quantization, graph compression, and image compression. We propose Quantum Entanglement Trees (QET) to address the QEM problem by leveraging the local orderliness of matrix elements.
  arXiv  Detail & Related papers  (2024-07-04T05:13:58Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting [13.270381125055275]
  We propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight. We develop an improved KL metric to determine optimal quantization scales for activation. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss.
  arXiv  Detail & Related papers  (2023-12-17T02:31:20Z)
• BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation [116.26521375592759]
  Quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation. Extreme quantization (1-bit weight/1-bit activations) of compactly-designed backbone architectures results in severe performance degeneration. This paper proposes a novel Quantization-Aware Training (QAT) method that can effectively alleviate performance degeneration.
  arXiv  Detail & Related papers  (2022-07-04T13:25:49Z)
• LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models [9.727062803700264]
  We introduce LUT-GEMM, an efficient kernel for quantized matrix multiplication. LUT-GEMM eliminates the resource-intensive dequantization process and reduces computational costs. We show experimentally that when applied to the OPT-175B model with 3-bit quantization, LUT-GEMM substantially accelerates token generation latency.
  arXiv  Detail & Related papers  (2022-06-20T03:48:17Z)
• OMPQ: Orthogonal Mixed Precision Quantization [64.59700856607017]
  Mixed precision quantization takes advantage of hardware's multiple bit-width arithmetic operations to unleash the full potential of network quantization. We propose to optimize a proxy metric, the concept of networkity, which is highly correlated with the loss of the integer programming. This approach reduces the search time and required data amount by orders of magnitude, with little compromise on quantization accuracy.
  arXiv  Detail & Related papers  (2021-09-16T10:59:33Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)
• VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization [19.66522714831141]
  We develop a new quantization solution called VecQ, which can guarantee minimal direct quantization loss and better model accuracy. In addition, in order to up the proposed quantization process during training, we accelerate the quantization process with a parameterized estimation and probability-based calculation.
  arXiv  Detail & Related papers  (2020-05-18T07:38:44Z)
• Kernel Quantization for Efficient Network Compression [59.55192551370948]
  Kernel Quantization (KQ) aims to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant performance loss. Inspired by the evolution from weight pruning to filter pruning, we propose to quantize in both kernel and weight level. Experiments on the ImageNet classification task prove that KQ needs 1.05 and 1.62 bits on average in VGG and ResNet18, respectively, to represent each parameter in the convolution layer.
  arXiv  Detail & Related papers  (2020-03-11T08:00:04Z)

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.