Skip to content

v0.56.0

Latest

Choose a tag to compare

@qaihm-bot qaihm-bot released this 19 Jun 01:24
· 105 commits to main since this release
ca623d4

Model improvements & fixes

  • Added evaluation support for Detectron2_Detection
  • Fixed dataset issue to reflect the correct on-device accuracy for BERT
  • Fixed accuracy discrepancy between torch and on-device for HuggingFace WaveLM Base Plus
  • Fixed input type to avoid mismatch for VideoMAE
  • Model changes to RTMDet that allow quantization to be w8a16
  • Correctly adding all context lengths to Qwen 2.5 7B VL metadata
  • PiperTTS variants correctly specify the language in their description.
  • Running demo.py on-device now works with custom input shapes
  • MMMU multimodal eval dataset and evaluator were added for VLMs
  • Ability run curated 100 prompts evaluation across LLMs/VLMs in evaluate.py
  • Added performance numbers for Samsung Galaxy S26 across all models.
  • XR 2 Gen 2 published perf numbers are now measured using Samsung Galaxy S22 instead of QCS8450 (Proxy), as Proxy devices will soon be deprecated in workbench.