QuantuneV2: Compiler-Based Local Metric-Driven Mixed Precision Quantization for Practical Embedded AI Applications

TL;DR

QuantuneV2 is a compiler-based mixed-precision quantization method that reduces runtime overhead and improves accuracy for embedded AI applications by performing inference only twice and optimizing the compilation process.

Contribution

It introduces a novel compiler-level approach for mixed-precision quantization that minimizes computational overhead and enhances model accuracy without retraining.

Findings

Achieved up to 10.28% accuracy improvement

Realized 12.52% speed increase over existing methods

Validated on five different neural network models

Abstract

Mixed-precision quantization methods have been proposed to reduce model size while minimizing accuracy degradation. However, existing studies require retraining and do not consider the computational overhead and intermediate representations (IR) generated during the compilation process, limiting their application at the compiler level. This computational overhead refers to the runtime latency caused by frequent quantization and dequantization operations during inference. Performing these operations at the individual operator level causes significant runtime delays. To address these issues, we propose QuantuneV2, a compiler-based mixed-precision quantization method designed for practical embedded AI applications. QuantuneV2 performs inference only twice, once before quantization and once after quantization, and operates with a computational complexity of O(n) that increases linearly with the number of model parameters. We also made the sensitivity analysis more stable by using local metrics like weights, activation values, the Signal to Quantization Noise Ratio, and the Mean Squared Error. We also cut down on computational overhead by choosing the best IR and using operator fusion. Experimental results show that QuantuneV2 achieved up to a 10.28 percent improvement in accuracy and a 12.52 percent increase in speed compared to existing methods across five models: ResNet18v1, ResNet50v1, SqueezeNetv1, VGGNet, and MobileNetv2. This demonstrates that QuantuneV2 enhances model performance while maintaining computational efficiency, making it suitable for deployment in embedded AI environments.