# Overview

The Qualcomm AI Runtime Development (QAIRT Dev) Python API provides a simple interface for executing ML models on QAIRT runtimes. [1](https://docs.qualcomm.com/doc/80-87189-2/topic/overview.html#f1)

It mirrors select capabilities and extends the features of existing QAIRT command line tools, while also providing an intuitive pythonic API for easy integration into ML workflows.

## Features

- - **ONNX Model Optimization**
    - - Transform and prepare ONNX models for LLM deployment before conversion.
    - Includes MHA→SHA conversion, sequence/context length (AR/CL) rewriting, model splitting, and custom graph transformations.
    - See [ONNX Optimizer API](https://docs.qualcomm.com/doc/80-87189-2/topic/qairt-optimizer.html) for details.
- - **Framework Model Conversion**
    - - Convert ONNX, Pytorch (1.x), TFLite framework models into DLC
    - Includes support for quantization and application of quantization encodings generated from [AIMET](https://github.qualcomm.com/qualcomm-ai/aimet/tree/develop/Examples).
- - **Compilation**
    - - Perform Ahead-of-Time (AOT) compilation on QAIRT backends to generate optimized binaries.
    - Supports compilation on HTP, HTP MCP and AIC backends.
- - **Model Execution**
    - - Execute models on python-native targets via Pybind wrappers on QAIRT APIs
    - Execute models on other targets (e.g android) via helper APIs that abstract platform-specific details
- - **Model Analysis**
    - - Generate profiling reports on all supported backends
    - Generate Op Trace and Qualcomm Hexagon Analysis Summary (QHAS) reports on HTP
- - **Gen AI Model Building and Execution**
    - - Convert, optimize, and compile Gen AI models for on-device inference using the [Gen AI Builder API](https://docs.qualcomm.com/doc/80-87189-2/topic/genai_builder.html#genai-builder) with a single `build()` call.
    - Configure model transformations, compilation options, LoRA adapters, and speculative decoding. See [Configuring the Gen AI Builder](https://docs.qualcomm.com/doc/80-87189-2/topic/genai_builder_configuration.html#genai-builder-configuration) for the full configuration reference.
    - Perform text generation and obtain metrics via [Generative AI Inference Engine](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-100/introduction.html) (Genie [2](https://docs.qualcomm.com/doc/80-87189-2/topic/overview.html#f2))
    - Construct Gen AI applications natively in python using simplified python bindings on Genie APIs.

## Support

- Non-Gen AI:

> 
> 
> - Frameworks: ONNX, TFLite, Pytorch
>     - Host Platforms: Linux-x86\_64 (Ubuntu 22.04 / 24.04), Linux-aarch64 (Ubuntu 24.04), Windows-x86\_64 (10+), Windows-arm64 (10+)
>     - Target Platforms: Linux-x86\_64 (Ubuntu 22.04 / 24.04), Linux-aarch64 (Ubuntu 24.04), Windows-arm64 (10+), Android-arm64, QNX
- Gen AI:

> 
> 
> - Frameworks: ONNX, GGUF
>     - Host Platforms: Linux-x86\_64 (Ubuntu 22.04)
>     - Target Platforms: Windows-arm64 (10+), Android-arm64

Note

- See [Appendix](https://docs.qualcomm.com/doc/80-87189-2/topic/appendix.html#appendix) for more information on supported Gen AI models
- **Host platform** indicates the platform where model conversion, optimization, and compilation are performed.
- **Target platform** indicates the platform where model execution is performed.

## Limitations

- The QAIRT Dev Python API is **currently in beta**. The API is thus subject to change between releases.
- QAIRT Dev Python API and QAIRT CLI tools are not yet at full parity. Please expect some differences in usage.

## Next steps

- [Setup](https://docs.qualcomm.com/doc/80-87189-2/topic/setup.html) – `qairt-dev` install and quick start.

- [1](https://docs.qualcomm.com/doc/80-87189-2/topic/overview.html#id1)

    - QAIRT is a component of the [Qualcomm AI Stack](https://www.qualcomm.com/developer/artificial-intelligence#overview).

- [2](https://docs.qualcomm.com/doc/80-87189-2/topic/overview.html#id2)

    - Genie is an associated component of the QAIRT Stack specifically for generative AI use cases.

Last Published: Aug 19, 2026

[Next Topic
Setup](https://docs.qualcomm.com/bundle/publicresource/80-87189-2/topics/setup.md)