Tool for robust segmentation of >100 important anatomical structures in CT and MR images

[ICCV 2025] AbdomenAtlas 3.0 (9,262 CT volumes + medical reports). These “superhuman” reports are more accurate, detailed, standardized, and generated faster than traditional human-made reports.

Official inference framework for 1-bit LLMs

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Open standard for machine learning interoperability

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

BiomedParse: A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities

A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.

Visualize ONNX models with model-explorer

Generative AI extensions for onnxruntime

Adapters and tools for lintrunner

Use safetensors with ONNX 🤗

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

AI Toolkit for Healthcare Imaging

Run compilers interactively from your web browser and interact with the assembly

An extension to trace, extract, and measure ops from running PyTorch models

ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.

Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning

Accelerate PyTorch models with ONNX Runtime

This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.

3D U-Net model for volumetric semantic segmentation written in pytorch