metal-flash-sdpa

kernels-community/metal-flash-sdpa

metal-flash-sdpa is a machine learning model from kernels-community. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for kernels. The card lists the license as apache-2.0.

[!CAUTION] 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 disr…

Downloads · 30 days

186

15% of all-time downloads

All-time downloads

1.2K

Public

Repo size

11.7 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.so3.7 MB · 96%

At a glance

Library: kernels
License: apache-2.0
Access: Public
Created: Jul 16, 2025
Updated: Sep 1, 2026
SHA: 18ac973f

Model card

From the Hugging Face model README

[!CAUTION] 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/metal-flash-sdpa 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/metal-flash-sdpa")
flash_attention_varlen = kernel_module.flash_attention_varlen

flash_attention_varlen(...)

Available functions

flash_attention_varlen
flash_attn_varlen_func
ops

Benchmarks

No benchmark available yet.

Library: kernels
License: apache-2.0
Created: Jul 16, 2025
Updated: Sep 1, 2026