Instructions to use replicate/flash-attn2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/flash-attn2 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/flash-attn2", version=1) - Notebooks
- Google Colab
- Kaggle
|
Download README.md from replicate/flash-attn2: direct link, hf CLI and curl.
- Browser
- Download file 500 Bytes
-
https://huggingface.co/replicate/flash-attn2/resolve/b0e71dbd4023a76fc61fc6a8c3a94de0a3fabd6f/README.md
- Command line
-
hf download hf://replicate/flash-attn2@b0e71dbd4023a76fc61fc6a8c3a94de0a3fabd6f/README.md
-
curl -L -o README.md https://huggingface.co/replicate/flash-attn2/resolve/b0e71dbd4023a76fc61fc6a8c3a94de0a3fabd6f/README.md
500 Bytes
metadata
library_name: kernels
license: bsd-3-clause
This is the repository card of kernels-community/flash-attn2 that has been pushed on the Hub. It was built to be used with the kernels library. This card was automatically generated.
How to use
Usage example not available.
Available functions
Function list not available.
Benchmarks
Benchmarking script is available for this kernel. Run kernels benchmark kernels-community/flash-attn2.