Skip to content

ONE Release 1.26.0

Latest
Compare
Choose a tag to compare
@mhs4670go mhs4670go released this 04 Jan 08:20
3f51fd8

Release Note 1.26.0

ONE Compiler

  • Support more Op(s): HardSwish, CumSum, BroadcastTo
  • Support more optimization option(s): decompose_softmax, decompose_hardswish, fuse_slice_with_tconv,
    fuse_mul_with_conv, remove_unnecessary_add, fuse_horizontal_fc_layers, common_subexpression_elimination,
    remove_unnecessary_transpose
  • one-quantize supports more option
    • Requantization option to convert TF2-quantized int8 model to uint8 model (--requantize)
    • A new option to automatically find mixed-precision configuration (--ampq)
    • A new option to save calibrated min/max values (--save_min_max)
    • Add new parameters for moving average calibration (--moving_avg_batch, --moving_avg_const)
  • Introduce q-implant that writes quantization parameters and weights into the circle model
  • Introduce minmax-embedder that embeds min/max values into the circle model