Selective Quantization Tuning for ONNX Models

• URL: http://arxiv.org/abs/2507.12196v1
• Date: Wed, 16 Jul 2025 12:46:04 GMT
• Title: Selective Quantization Tuning for ONNX Models
• Authors: Nikolaos Louloudakis, Ajitha Rajan,
• Abstract summary: We propose TuneQn, a suite enabling selective quantization, deployment and execution of ONNX models.<n>TuneQn generates selectively quantized ONNX models, deploys them on different hardware, measures performance on metrics like accuracy and size.<n>We show that TuneQn effectively performs selective quantization and tuning, selecting ONNX model candidates with up to a $54.14$% reduction in accuracy loss.
• Score: 2.6754376830313817
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Quantization is a process that reduces the precision of deep neural network models to lower model size and computational demands, often at the cost of accuracy. However, fully quantized models may exhibit sub-optimal performance below acceptable levels and face deployment challenges on low-end hardware accelerators due to practical constraints. To address these issues, quantization can be selectively applied to only a subset of layers, but selecting which layers to exclude is non-trivial. To this direction, we propose TuneQn, a suite enabling selective quantization, deployment and execution of ONNX models across various CPU and GPU devices, combined with profiling and multi-objective optimization. TuneQn generates selectively quantized ONNX models, deploys them on different hardware, measures performance on metrics like accuracy and size, performs Pareto Front minimization to identify the best model candidate and visualizes the results. To demonstrate the effectiveness of TuneQn, we evaluated TuneQn on four ONNX models with two quantization settings across CPU and GPU devices. As a result, we demonstrated that our utility effectively performs selective quantization and tuning, selecting ONNX model candidates with up to a $54.14$% reduction in accuracy loss compared to the fully quantized model, and up to a $72.9$% model size reduction compared to the original model.

Related papers

• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models [88.80146574509195]
  Quantization is a promising approach for reducing memory overhead and accelerating inference. We propose a novel-aware quantization (ZSAQ) framework for the zero-shot quantization of various PLMs.
  arXiv  Detail & Related papers  (2023-10-20T07:09:56Z)
• FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search [50.07268323597872]
  We propose the first one-shot mixed-precision quantization search that eliminates the need for retraining in both integer and low-precision floating point models. With integer models, we increase the accuracy of ResNet-18 on ImageNet by 1.31% and ResNet-50 by 0.90% with equivalent model cost over previous methods. For the first time, we explore a novel mixed-precision floating-point search and improve MobileNetV2 by up to 0.98% compared to prior state-of-the-art FP8 models.
  arXiv  Detail & Related papers  (2023-08-07T04:17:19Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization [7.392278887917975]
  We propose a mixed-precision post training quantization approach that assigns different numerical precisions to tensors in a network based on their specific needs. Our experiments demonstrate latency reductions compared to a 16-bit baseline of $25.48%$, $21.69%$, and $33.28%$ respectively.
  arXiv  Detail & Related papers  (2023-06-08T02:18:58Z)
• Vertical Layering of Quantized Neural Networks for Heterogeneous Inference [57.42762335081385]
  We study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. We can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model.
  arXiv  Detail & Related papers  (2022-12-10T15:57:38Z)
• AMED: Automatic Mixed-Precision Quantization for Edge Devices [3.5223695602582614]
  Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. Mixed-precision quantization offers better utilization of customized hardware that supports arithmetic operations at different bitwidths.
  arXiv  Detail & Related papers  (2022-05-30T21:23:22Z)
• One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment [36.75157407486302]
  We propose a method to train a model for all quantization that supports diverse bit-widths. We use wavelet decomposition and reconstruction to increase the diversity of weights. Our method can achieve accuracy comparable to dedicated models trained at the same precision.
  arXiv  Detail & Related papers  (2021-05-04T08:10:50Z)
• 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)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)
• 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)
• 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)
• SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks [29.187848543158992]
  We present a new quantized neural network optimization approach, quantized weight averaging (SQWA) The proposed approach includes floating-point model training, direct quantization of weights, capturing multiple low-precision models, averaging the captured models, and fine-tuning it with low-learning rates. With SQWA training, we achieved state-of-the-art results for 2-bit QDNNs on CIFAR-100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-02-02T07:02:51Z)

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.