Developed quantization features for ONNX models within the microsoft/Olive repository, focusing on hardware-aware model optimization using Python and PyTorch. Introduced the QuarkQuantization pass, enabling support for multiple data types and quantization algorithms to streamline deployment across diverse hardware. Additionally, created a MobileNetV3 ONNX quantization optimization recipe in microsoft/olive-recipes, leveraging TIMM and Olive workflows to enhance CPU and NPU inference performance. Ensured code reliability by implementing unit tests and addressing lint issues, contributing to overall stability and quality assurance. The work emphasized robust machine learning model optimization and quantization, supporting efficient end-to-end inference pipelines for production environments.