Metadata-Version: 2.2
Name: qairt-dev
Version: 0.5.0
Summary: The Qualcomm AI Runtime Development (QAIRT-DEV) package provides a simple python interface for executing ML models on QAIRT runtimes
Author-email: "Qualcomm Technologies, Inc." <qairt-dev-support@qti.qualcomm.com>
Maintainer-email: qairt-dev-support <qairt-dev-support@qti.qualcomm.com>
License: Proprietary
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Operating System :: Microsoft :: Windows :: Windows 10
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Requires-Python: <3.11,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE.pdf
Requires-Dist: aenum==3.1.15
Requires-Dist: click<9.0.0,>=8.1.8
Requires-Dist: cryptography<46.0.0,>=45.0.3
Requires-Dist: numpy==1.26.4
Requires-Dist: paramiko==3.5.1
Requires-Dist: pip<26.0,>=25.0
Requires-Dist: protobuf==6.31.0
Requires-Dist: pydantic<2.9.0,>=2.8.2
Requires-Dist: pyyaml<7.0.0,>=6.0.2
Requires-Dist: rich==13.9.4
Requires-Dist: safetensors==0.4.3
Requires-Dist: sentencepiece==0.2.0
Requires-Dist: setuptools<76.0,>=75.0
Requires-Dist: transformers==4.44.0
Requires-Dist: types-paramiko==3.5.0.20250516
Provides-Extra: onnx
Requires-Dist: onnx==1.19.1; extra == "onnx"
Requires-Dist: onnx_ir==0.1.12; extra == "onnx"
Requires-Dist: onnxruntime==1.23.2; extra == "onnx"
Requires-Dist: onnxruntime-genai==0.8.2; extra == "onnx"
Requires-Dist: onnxsim==0.4.36; extra == "onnx"
Requires-Dist: onnx-graphsurgeon==0.5.8; extra == "onnx"
Requires-Dist: onnxscript==0.5.6; extra == "onnx"
Requires-Dist: scipy==1.15.3; extra == "onnx"
Requires-Dist: islpy==2025.2.5; platform_system == "Linux" and extra == "onnx"
Requires-Dist: gguf==0.9.1; extra == "onnx"
Provides-Extra: torch
Requires-Dist: torch==2.4.1; extra == "torch"
Requires-Dist: torchvision==0.19.1; extra == "torch"

# Qualcomm AI Runtime Development (QAIRT-DEV) package

[[Docs]](https://docs.qualcomm.com/bundle/publicresource/topics/80-87189-2/overview.html) [[Discord Forums]](https://discord.com/invite/qualcommdevelopernetwork)
 
The Qualcomm AI Runtime (QAIRT) Development Python API provides a simple interface for executing ML models on [QAIRT](https://www.qualcomm.com/developer/artificial-intelligence#overview>) runtimes

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
--------

- **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 AOT compilation on QAIRT backends to generate optimized binaries.
   - Perform compiler optimization using tuning API on HTP
   - 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 a builder object with a single API call.
   - Perform text generation and obtain metrics via [Generative AI Inference Engine](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-100/introduction.html)
   - Construct Gen AI applications natively in python using simplified python bindings on Genie APIs.

## Install

QAIRT Dev is available via pip:

```shell
pip install qairt-dev
```

## Getting Started

QAIRT Dev documentation can be found [here](https://docs.qualcomm.com/bundle/publicresource/topics/80-87189-2/overview.html)

## Need help?

* Discord Forums: [Qualcomm Developer Network - AI](https://discord.com/invite/qualcommdevelopernetwork)
* Support: qairt-dev-support@qti.qualcomm.com

## LICENSE

Qualcomm AI Runtime Development (QAIRT-DEV) package is Proprietary licensed. See _LICENSE.pdf_ for further details.
