version 1.20.0

Release of the AI Model Efficiency toolkit package

• User guide: https://quic.github.io/aimet-pages/releases/1.20.0/user_guide/index.html
• API documentation: https://quic.github.io/aimet-pages/releases/1.20.0/api_docs/index.html
• Documentation main page: https://quic.github.io/aimet-pages/index.html

version 1.19.1.py37

Release of the AI Model Efficiency toolkit package

• PyTorch: Added CLE support for Conv1d, ConvTranspose1d and Depthwise Separable Conv1d layers
• PyTorch: Added High-Bias Fold support for Conv1D layer
• PyTorch: Modified Elementwise Concat Op to support any number of tensors
• Minor dependency fixes

User guide: https://quic.github.io/aimet-pages/releases/1.19.1/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.19.1/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

NOTE: This release is functionally equivalent to the 1.19.1 release (https://github.com/quic/aimet/releases/tag/1.19.1). But it has NOT undergone rigorous testing. It has been created only for compatibility with Google Colab.

version 1.19.1

Release of the AI Model Efficiency toolkit package

• PyTorch: Added CLE support for Conv1d, ConvTranspose1d and Depthwise Separable Conv1d layers
• PyTorch: Added High-Bias Fold support for Conv1D layer
• PyTorch: Modified Elementwise Concat Op to support any number of tensors
• Minor dependency fixes

User guide: https://quic.github.io/aimet-pages/releases/1.19.1/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.19.1/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

version 1.18.0.py37

Release of the AI Model Efficiency toolkit package

Release Notes

• Multiple bug fixes
• Additional feature examples for PyTorch and TensorFlow

User guide: https://quic.github.io/aimet-pages/releases/1.18.0/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.18.0/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

NOTE: This release is functionally equivalent to the 1.18.0 release (https://github.com/quic/aimet/releases/tag/1.18.0). But it has NOT undergone rigorous testing. It has been created only for compatibility with Google Colab.

version 1.18.0

Release of the AI Model Efficiency toolkit package

Release Notes

• Multiple bug fixes
• Additional feature examples for PyTorch and TensorFlow

User guide: https://quic.github.io/aimet-pages/releases/1.18.0/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.18.0/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

version 1.17.0.py37

Release of the AI Model Efficiency toolkit package

Release Notes

• Add Adaround TF feature
• Added Examples for Torch quantization, and Channel Pruning & Spatial SVD compression

User guide: https://quic.github.io/aimet-pages/releases/1.17.0.py37/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.17.0.py37/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

NOTE: This release is functionally equivalent to the 1.17.0 release (https://github.com/quic/aimet/releases/tag/1.17.0). But it has NOT undergone rigorous testing. It has been created only for compatibility with Google Colab.

version 1.17.0

Release of the AI Model Efficiency toolkit package

Release Notes

• Add Adaround TF feature
• Added Examples for Torch quantization, and Channel Pruning & Spatial SVD compression

User guide: https://quic.github.io/aimet-pages/releases/1.17.0/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.17.0/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

version 1.16.2.py37

Release of the AI Model Efficiency toolkit package for Python 3.7 environments (such as Google Colab).

Release notes:

• Added a new post-training quantization feature called AdaRound, which stands for AdaptiveRounding
• Quantization simulation and QAT now also support recurrent layers (RNN, LSTM, GRU)

User guide: https://quic.github.io/aimet-pages/releases/1.16.2.py37/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.16.2.py37/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

NOTE: This release is functionally equivalent to the 1.16.2 release (https://github.com/quic/aimet/releases/tag/1.16.2). But it has NOT undergone rigorous testing. It has been created only for compatibility with Google Colab.

version 1.16.2

Release of the AI Model Efficiency toolkit package

Release notes:

• Added a new post-training quantization feature called AdaRound, which stands for AdaptiveRounding
• Quantization simulation and QAT now also support recurrent layers (RNN, LSTM, GRU)

User guide: https://quic.github.io/aimet-pages/releases/1.16.2/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.16.2/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

version 1.16.1.py37

Release of the AI Model Efficiency toolkit package for Python 3.7 environments (such as Google Colab).
User guide: https://quic.github.io/aimet-pages/releases/1.16.1.py37/user_guide/index.html
API documentation: https://quic.github.io/aimet-pages/releases/1.16.1.py37/api_docs/index.html
Documentation main page: https://quic.github.io/aimet-pages/index.html

NOTE: This release has NOT undergone rigorous testing. It has been created only for compatibility with Google Colab. For the most stable release (python 3.6), please see the latest python 3.6 releases (default) at https://github.com/quic/aimet/releases