During May 2025, Satreysa contributed to the microsoft/onnxruntime-genai repository by adding quantized model layer support for q_norm and k_norm, addressing the need for accurate quantized attention in newer large language models. Satreysa implemented these layers as Tensor modules in Python, ensuring that weights and biases were correctly mapped during model loading to preserve quantization behavior. This work leveraged deep learning and model optimization skills to improve compatibility with quantized LLMs, reducing deployment risk and enhancing inference speed and memory efficiency for generative AI workloads. The contribution demonstrated a focused, in-depth approach to advancing quantization support in production environments.