v0.7.0

[baijumeswani]

Release Notes

We are excited to announce the release of onnxruntime-genai version 0.7.0. Below are the key updates included in this release:

1. Support for a wider variety of QNN NPU models (such as Deepseek R1)
2. Remove onnxruntime-genai static library. All language bindings now interface with onnxruntime-genai through the onnxruntime-genai shared library.

• All return types from onnxruntime-genai python package is now a numpy array type.

4. Abstract away execution provider specific code into shared libraries of their own (for example onnxruntime-genai-cuda for cuda, and onnxruntime-genai-dml for dml). This allows using the onnxruntime-genai-cuda package to also work on non cuda machines (as an example).
5. Support for multi-modal models (text, speech, and vision) such as phi4-multi-modal.
6. Add an IChatClient implementation to the onnxruntime-genai C# bindings.
7. Expose the model type through the Python bindings.
8. Code and performance improvements for DML EP.

This release also includes several bug fixes that resolve issues reported by users.

---

This discussion was created from the release v0.7.0.

[Eugene-M]

Could you please update the code samples to explain how to use these changes?

[abishekpadaki]

Are there any example scripts for NPU inference with this update?