Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference

• URL: http://arxiv.org/abs/2505.14638v1
• Date: Tue, 20 May 2025 17:26:12 GMT
• Title: Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
• Authors: Tomer Gafni, Asaf Karnieli, Yair Hanani,
• Abstract summary: We propose a novel hardware-efficient quantization and inference scheme that exploits hardware advantages with minimal accuracy degradation.<n>We develop a novel quantization algorithm, dubbed Dual Precision Quantization (DPQ), that leverages the unique structure of our scheme without introducing additional inference overhead.
• Score: 3.7687375904925484
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to grow, posing challenges in latency and memory efficiency. To meet these constraints, post-training quantization has emerged as a promising solution. In this paper, we propose a novel hardware-efficient quantization and inference scheme that exploits hardware advantages with minimal accuracy degradation. Specifically, we introduce a W4A8 scheme, where weights are quantized and stored using 4-bit integer precision, and inference computations are performed using 8-bit floating-point arithmetic, demonstrating significant speedups and improved memory utilization compared to 16-bit operations, applicable on various modern accelerators. To mitigate accuracy loss, we develop a novel quantization algorithm, dubbed Dual Precision Quantization (DPQ), that leverages the unique structure of our scheme without introducing additional inference overhead. Experimental results demonstrate improved performance (i.e., increased throughput) while maintaining tolerable accuracy degradation relative to the full-precision model.

Related papers

• Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics [65.37942405146232]
  We present a novel type of overload that carries with extremely lightweight state elements, achieved through ultra-low-precision quantization.<n>The proposed SOLO achieves substantial memory savings (approximately 45 GB when training a 7B model) with minimal accuracy loss.
  arXiv  Detail & Related papers  (2025-05-01T06:47:45Z)
• Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks [10.229120811024162]
  deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization. We propose a novel methodology to apply them jointly via a lightweight gradient-based search.
  arXiv  Detail & Related papers  (2024-07-01T08:07:02Z)
• Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip [0.9187138676564589]
  We present High Granularity Quantization (HGQ), an innovative quantization-aware training method. HGQ fine-tune the per-weight and per-activation precision by making them optimizable through gradient descent. This approach enables ultra-low latency and low power neural networks on hardware capable of performing arithmetic operations.
  arXiv  Detail & Related papers  (2024-05-01T17:18:46Z)
• On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks [52.97107229149988]
  We propose an On-Chip Hardware-Aware Quantization framework, performing hardware-aware mixed-precision quantization on deployed edge devices. For efficiency metrics, we built an On-Chip Quantization Aware pipeline, which allows the quantization process to perceive the actual hardware efficiency of the quantization operator. For accuracy metrics, we propose Mask-Guided Quantization Estimation technology to effectively estimate the accuracy impact of operators in the on-chip scenario.
  arXiv  Detail & Related papers  (2023-09-05T04:39:34Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Low-bit Shift Network for End-to-End Spoken Language Understanding [7.851607739211987]
  We propose the use of power-of-two quantization, which quantizes continuous parameters into low-bit power-of-two values. This reduces computational complexity by removing expensive multiplication operations and with the use of low-bit weights.
  arXiv  Detail & Related papers  (2022-07-15T14:34:22Z)
• Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets [7.5195830365852085]
  We propose a novel sub 8-bit quantization aware training algorithm for all components of a 250K parameter feedforward, streaming, state-free keyword spotting model. We conduct large scale experiments, training on 26,000 hours of de-identified production, far-field and near-field audio data.
  arXiv  Detail & Related papers  (2022-07-13T17:46:08Z)
• Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition [65.7040645560855]
  We propose Q-ASR, an integer-only, zero-shot quantization scheme for ASR models. We show negligible WER change as compared to the full-precision baseline models. Q-ASR exhibits a large compression rate of more than 4x with small WER degradation.
  arXiv  Detail & Related papers  (2021-03-31T06:05:40Z)
• 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)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

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.