Skip to content

Quantization-Aware Training, Python 3.8.6, Bugfixes

Pre-release
Pre-release
Compare
Choose a tag to compare
@rotx-maxim rotx-maxim released this 26 Jan 23:50
20210126
d24dc69
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

The main improvement in this release is enabling Quantization-Aware Training (QAT) by default.
Additionally, it upgrades to:

  • PyTorch 1.71, Python 3.8.6, CUDA 11
    There is also a number of bug fixes and documentation improvements.

Please follow the instructions in README.md to upgrade (ignore the zip files in the Release).

Assets 2
Loading