Developed the initial integration of the VitisAI Execution Provider for ONNX Runtime within the microsoft/onnxruntime-genai repository, enabling hardware-accelerated inference on Vitis AI-capable devices. Focused on C++ development and API design, the work introduced configuration options to register a custom operations library, allowing for hardware-optimized inference workflows. The implementation established a foundation for future hardware-tested validation and continuous integration support. By aligning with software architecture best practices, this feature enhanced enterprise performance and reduced latency for generative AI workloads. No major bugs were reported during the period, reflecting a stable and focused approach to feature delivery and integration.