Greg Yang
Results
2
issues of
Greg Yang
Added single-batch batchnorm kernel. We also add `quadpy` as a dependency for the numerical integration required.
# 🚀 Feature request This request is to open up a discussion on 1) whether it makes sense to implement [Maximal Update Parametrization (abbreviated muP)](http://arxiv.org/abs/2203.03466) in Huggingface, 2) if so,...
WIP