Skip to content

Intel® Neural Compressor v1.11 Release

Compare
Choose a tag to compare
@ftian1 ftian1 released this 15 Apr 14:04
· 2206 commits to master since this release

Features

  • Quantization
    • Supported QDQ as experimental quantization format for ONNX Runtime
    • Improved FX symbolic tracing for PyTorch
    • Supported multi-metrics for quantization tuning
  • Knowledge distillation
    • Improved distillation algorithm for intermediate layer knowledge transfer
  • Productivity
    • Improved quantization productivity for ONNX Runtime through GUI
    • Improved PyTorch INT8 model save/load methods
  • Ecosystem
    • Upstreamed INC quantized Yolov3, DenseNet, Mask-Rcnn, Yolov4 models to ONNX Model Zoo
    • Became PyTorch ecosystem tool shortly after published PyTorch INC tutorial
  • Examples
    • Added INC quantized ResNet50 v1.5 and BERT-Large model for IPEX
    • Supported dynamic quantization & weight sharing on bare metal reference engine