MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI
Authors:
- 26 October 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Abstract
Quantized Neural Networks (QNN) with extremely low-bitwidth data have proven promising in efficient storage and computation on edge devices. To further reduce the accuracy drop while increasing speedup, layer-wise mixed-precision quantization (MPQ) becomes a popular solution. However, existing algorithms for exploring MPQ schemes are limited in flexibility and efficiency. Comprehending the complex impacts of different MPQ schemes on post-training quantization and quantization-aware training results is a challenge for conventional methods. Furthermore, an end-to-end framework for the optimization and deployment of MPQ models is missing in existing work.In this paper, we propose the MiCo framework, a holistic MPQ exploration and deployment framework for edge AI applications. The framework adopts a novel optimization algorithm to search for optimal quantization schemes with the highest accuracies while meeting latency constraints. Hardware-aware latency models are built for different hardware targets to enable fast explorations. After the exploration, the framework enables direct deployment from PyTorch MPQ models to bare-metal C codes, leading to end-to-end speedup with minimal accuracy drops.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference2024
- Mix-GEMM: An efficient HW-SW Architecture for Mixed-Precision Quantized Deep Neural Networks Inference on Edge Devices2023
- DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUsIEEE Transactions on Computers, 2021
- A Mixed-Precision RISC-V Processor for Extreme-Edge DNN Inference2020
- ZeroQ: A Novel Zero Shot Quantization Framework2020
- HAQ: Hardware-Aware Automated Quantization With Mixed Precision2019
- UNPU: An Energy-Efficient Deep Neural Network Accelerator With Fully Variable Weight Bit PrecisionIEEE Journal of Solid-State Circuits, 2018
- Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network2018
- From high-level deep neural models to FPGAs2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998