Instructions to use replicate/aiter-flash-attn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/aiter-flash-attn 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/aiter-flash-attn", version=1) - Notebooks
- Google Colab
- Kaggle
|
Download README.md from replicate/aiter-flash-attn: direct link, hf CLI and curl.
- Browser
- Download file 1.06 kB
-
https://huggingface.co/replicate/aiter-flash-attn/resolve/main/README.md
- Command line
-
hf download hf://replicate/aiter-flash-attn/README.md
-
curl -L -o README.md https://huggingface.co/replicate/aiter-flash-attn/resolve/main/README.md
1.06 kB
metadata
library_name: kernels
license: mit
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 is the repository card of kernels-community/aiter-flash-attn 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
# make sure `kernels` is installed: `pip install -U kernels`
from kernels import get_kernel
kernel_module = get_kernel("kernels-community/aiter-flash-attn")
__kernel_metadata__ = kernel_module.__kernel_metadata__
__kernel_metadata__(...)
Available functions
__kernel_metadata__flash_attn_funcflash_attn_varlen_funcflash_attn_with_kvcachemha_set_implmha_set_use_fused_bwd_kernelmha_set_use_int64_strides