Instructions to use replicate/sage_attention with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/sage_attention with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/sage_attention", version=1) - Notebooks
- Google Colab
- Kaggle
File size: 335 Bytes
937cfd9 6d5dee5 937cfd9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
description = "Flake for Torch kernel extension";
inputs = {
kernel-builder.url = "github:huggingface/kernel-builder/redo-capabilities";
};
outputs = { self, kernel-builder, }:
kernel-builder.lib.genFlakeOutputs {
path = ./.;
rev = self.shortRev or self.dirtyShortRev or self.lastModifiedDate;
};
}
|