Instructions to use replicate/layer_norm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/layer_norm with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("replicate/layer_norm") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from replicate/layer_norm: direct link, hf CLI and curl.
- Browser
- Download file 677 Bytes
-
https://huggingface.co/replicate/layer_norm/resolve/main/README.md
- Command line
-
hf download hf://replicate/layer_norm/README.md
-
curl -L -o README.md https://huggingface.co/replicate/layer_norm/resolve/main/README.md
677 Bytes
metadata
tags:
- kernels
Starting from September 13, 2026, we will be removing the "model" type repositories of kernels (e.g., kernels-community/flash-attn3). Make sure you're using a latest version of kernels. If you face any disruption, please report them here: https://github.com/huggingface/kernels/issues/new.
This repository will soon be deleted as it's now deprecated. Please use kernels-community/layer-norm.
This CUDA extension implements fused dropout + residual + LayerNorm from the flash-attention repo.