# 0.10.1

## 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 (2.47.0, 2.48.0 (Default), 2.49.0)

Note

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

## Resolved Issues

- Fixed LoRA Gather activation-encoding injection incorrectly skipping embedding weights with a
missing `bw` (bitwidth) key, which was silently treated as already HTP-legal (>=8-bit) and left
unpatched, letting the converter bake in an unsupported sub-8-bit activation. Injection now
correctly validates weight bitwidth before deciding whether to skip.
- Fixed the ONNX framework utility packages being omitted from the `qairt-dev` wheel, causing
`pip install qairt-dev` to be missing ONNX Model API support.

Last Published: Aug 26, 2026

[Previous Topic
Known Issues](https://docs.qualcomm.com/bundle/publicresource/80-87189-2/topics/0_10_0.md)