A memory balanced and communication efficient FullyConnected layer with CrossEntropyLoss model parallel implementation in PyTorch
-
Updated
Jun 11, 2020 - Python
#
half-precision
Here are 2 public repositories matching this topic...
Python module which finds the IEEE-754 representation of a floating point number.
-
Updated
Mar 1, 2024 - Python
Improve this page
Add a description, image, and links to the half-precision topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the half-precision topic, visit your repo's landing page and select "manage topics."