For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python module

max.experimental.nn.norm

Normalization layers for MAX neural networks.

Normalization layers

`GemmaRMSNorm`	Gemma-style root mean square normalization.
`GroupNorm`	Group normalization over the channel axis of the input.
`LayerNorm`	Layer normalization over the last dimension of the input.
`RMSNorm`	Root mean square normalization over the last dimension of the input.

`rms_norm`