Hello fellow Nvidia Jetson enthusiasts,
Below is a video demonstration of ruining the inference of the Phi-3.5-vision-instruct-onnx(microsoft/Phi-3.5-vision-instruct-onnx · Hugging Face) model using ONNX Runtime GenAI(GitHub - microsoft/onnxruntime-genai: Generative AI extensions for onnxruntime) using GPU.