# 0.8.1

## Release Information

- OS & Framework support - Tested with the following configurations:

> 
> 
> - Non-Gen AI:
> 
> 
> 
> > 
> > 
> > - Frameworks: ONNX, TFLite, Pytorch
> >         - Host Platforms: Linux-x86\_64 (Ubuntu 22.04, Ubuntu 24.04), Linux-aarch64 (Ubuntu 24.04, Python 3.12), Windows-x86\_64 (10+), Windows-arm64 (10+)
> >         - Target Platforms: Linux-x86\_64 (Ubuntu 22.04, Ubuntu 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, Ubuntu 24.04)
> >         - Target Platforms: Android-arm64, Linux-aarch64
- QAIRT SDK - Tested with version (2.45.0, 2.46.0, 2.47.0(Default))

Note

For QAIRT SDK, other supported SDK versions can be listed using `qairt-vm fetch --list`.

## Resolved Issues

- Pinned `safetensors==0.4.3` and `transformers==4.57.1` to fix incorrect weight values during model preparation caused by `safetensors` 0.8.0 interface changes, which corrupted quantization encodings and broke on-device inference.
- Fixed `pip install qairt-dev` being incorrectly restricted to Python 3.12 on all platforms in 0.8.0. Python 3.10 and 3.12 are now supported on x86/Windows as expected; Python 3.12 is still required on Linux-aarch64.

## Documentation

- Clarified in the setup section that on Linux-aarch64, only Python 3.12 is supported (Python 3.10 is not available on that platform).

Last Published: Jun 19, 2026

[Previous Topic
Known Issues](https://docs.qualcomm.com/bundle/publicresource/80-87189-2/topics/0_8_0.md)