Skip to content

v0.49.1

Choose a tag to compare

View all tags
@qaihm-bot qaihm-bot released this 24 Mar 02:55
· 548 commits to main since this release
v0.49.1
c7381f9
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

General Updates

  • Added quantized variants for DETR-ResNet50, DETR-ResNet50-DC5, DETR-ResNet101, and DETR-ResNet101-DC5
    Removed BiseNet and BGNet due to licensing concerns
  • Llama 3.2 3B Instruct SSD variant uses Self Speculative Decoding (SSD), inference acceleration solution that achieves on-target speed up with guaranteed output accuracy identical to the base model. Choose this variant over llama_v3_2_3b_instruct for faster token generation on supported devices.
  • Updated performance & accuracy data from latest version of AI Hub Workbench

Bug Fixes

  • Fixed batchnorm unfolding issue in MediaPipe Hand Gesture, enabling the model to be fully NPU-resident when quantized with TFLite
  • Fixed non-determinism in loading the BSD300 dataset. This previously caused us to report incorrect accuracy data for several super resolution models.
  • MeloTTS has been updated to work around an HTP issue with summation that produced incorrect shapes at runtime. This update is available only via the export script and is not yet available with pre-generated assets.
Assets 2
Loading