# Customize LiteRT

LiteRT and its libraries are built as part of the Qualcomm Linux build
along with the Qualcomm IM SDK. Therefore, building Qualcomm Linux is
optional. You can build Qualcomm Linux in certain scenarios, such as
when you want to change the LiteRT library version. To recompile LiteRT
as part of the Qualcomm Linux build along with the Qualcomm IM SDK, see
[Qualcomm Linux Build Guide](https://docs.qualcomm.com/doc/80-80022-254)

To enhance developer experience, the Qualcomm IM SDK provides the
`qtimltflite` GStreamer-based plug-in, which performs LiteRT model
inference.

For more information, see the following:

- [Qualcomm IM SDK](https://docs.qualcomm.com/doc/80-80022-50) documentation
- [qtimltflite](https://docs.qualcomm.com/doc/80-80022-50/topic/qtimltflite.html) plug-in documentation
- [Develop your own AI/ML application](https://docs.qualcomm.com/doc/80-80022-15B/topic/develop-your-own-application.html)

Last Published: May 14, 2026

[Previous Topic
Deploy LiteRT as a Python application](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/deploy-litert-as-a-python-application.md) [Next Topic
Run an ONNX model on NPU using ORT](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/run-an-onnx-model-using-ort.md)