Published December 20, 2024 | Version v0.4.0
Software Open

QONNX

  • 1. AMD
  • 2. Heidelberg University
  • 3. MIT
  • 4. CERN
  • 5. UC San Diego

Description

Highlights:

  • Channels-last conversion improvements and support for branching topologies (#148 #149 #163)
  • New rounding modes in Quant (#134)
  • QuantLSTM QCDQ representation (#79)
  • Inference cost breakdown (#101)
  • Channel pruning and quantization utilities (#71 #94)

Full list of merged PRs: https://github.com/fastmachinelearning/qonnx/milestone/4?closed=1

Notes

If you use this software, please cite it as below.

Files

fastmachinelearning/qonnx-v0.4.0.zip

Files (1.4 MB)

Name Size Download all
md5:27dce1244628d69d9a008766f85f32c3
1.4 MB Preview Download

Additional details

Related works