MIGraphX examples

MIGraphX examples#

2026-10-12

3 min read time

Applies to Linux

The MIGraphX repository includes examples for common inference workflows. Each example below is documented in its README file. Follow the linked path in the MIGraphX GitHub repository to build and run the example.

Getting started examples#

These examples teach core MIGraphX workflows. Start here if you are new to the library.

Example	Target user	What it demonstrates
Parse, load, and save a model	C++ application developers	Parse ONNX models, inspect graphs, and save or load programs in MessagePack or JSON format.
cpp_mnist	C++ application developers	End-to-end inference: parse ONNX, compile for GPU or CPU, quantize, prepare inputs, and evaluate.
migraphx_driver	Model integrators	Command-line usage of `migraphx-driver` for read, compile, run, verify, and perf without writing code.

MIGraphX API examples#

Examples under examples/migraphx/ cover MIGraphX-specific utilities and advanced C++ API usage.

Example	Target user	What it demonstrates
cpp_parse_load_save	C++ application developers	Parse, load, and save graph programs.
cpp_dynamic_batch	C++ application developers	Run programs with dynamic batch sizes using `dynamic_dimension` objects.
cpp_trace_callback	MIGraphX contributors and debuggers	Inspect operator output buffers during evaluation with `program::run_trace`.
export_frozen_graph_tf1	Model integrators	Export frozen TensorFlow 1 graphs for MIGraphX ingestion.
export_frozen_graph_tf2	Model integrators	Export frozen TensorFlow 2 graphs for MIGraphX ingestion.

Vision examples#

Examples under examples/vision/ cover image classification, detection, segmentation, and super resolution.

Example	Target user	What it demonstrates
cpp_mnist	C++ application developers	MNIST digit classification with the C++ API.
python_resnet50	Python application developers	ResNet50 V2 inference in Python via a Jupyter notebook.
python_nfnet	Python application developers	NFNet inference and ONNX Runtime comparison.
python_super_resolution	Python application developers	Super resolution inference.
python_unet	Python application developers	U-Net segmentation inference.
python_3dunet	Python application developers	3D U-Net inference.
python_yolov4	Python application developers	YOLOv4 object detection inference.
python_yolo26	Python application developers	YOLO26 object detection inference.

Natural language processing examples#

Examples under examples/nlp/ cover question answering and speech recognition.

Example	Target user	What it demonstrates
python_bert_squad	Python application developers	BERT question answering on SQuAD.
python_rnnt	Python application developers	RNN-T speech recognition inference.

Diffusion examples#

Examples under examples/diffusion/ cover text-to-image diffusion models.

Example	Target user	What it demonstrates
python_stable_diffusion_21	Python application developers	Stable Diffusion 2.1 text-to-image inference.
python_stable_diffusion_xl	Python application developers	Stable Diffusion XL text-to-image inference.
python_stable_diffusion_3	Python application developers	Stable Diffusion 3 text-to-image inference.
python_flux	Python application developers	Flux text-to-image inference.
python_controlnet_canny_sd_15	Python application developers	ControlNet Canny edge guidance with Stable Diffusion 1.5.

Transformer examples#

Examples under examples/transformers/ cover large language model and speech model inference.

Example	Target user	What it demonstrates
python_llama2	Python application developers	Llama 2 inference.
python_whisper	Python application developers	Whisper automatic speech recognition.

ONNX Runtime examples#

Examples under examples/onnxruntime/ show MIGraphX integration through the ONNX Runtime execution provider.

Example	Target user	What it demonstrates
resnet50	ONNX Runtime users	ResNet50 inference through ONNX Runtime with the MIGraphX execution provider.
inceptionV3	ONNX Runtime users	InceptionV3 inference through ONNX Runtime with the MIGraphX execution provider.