QuantuneV2: Compiler-based local metric-driven mixed precision quantization for practical embedded AI applications
- 17 January 2025
- journal article
- Published by Elsevier in Future Generation Computer Systems
- Vol. 166
Abstract
No abstract availableAll Related Versions
Funding Information
- Institute for Information and Communications Technology Promotion
This publication has 16 references indexed in Scilit:
- Complexity-Aware Layer-Wise Mixed-Precision Schemes With SQNR-Based Fast AnalysisIEEE Access, 2023
- Post Training Mixed Precision Quantization of Neural Networks using First-Order Information2023
- Quantune: Post-training quantization of convolutional neural networks using extreme gradient boosting for fast deploymentFuture Generation Computer Systems, 2022
- Mixed Precision Low-Bit Quantization of Neural Network Language Models for Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Low-bit Quantization of Neural Networks for Efficient Inference2019
- HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision2019
- Data-Free Quantization Through Weight Equalization and Bias Correction2019
- Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss2019
- LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks2018
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018