FlashAttention-4 (CuTeDSL)

FlashAttention-4 is a CuTeDSL-based implementation of FlashAttention for Hopper and Blackwell GPUs.

Installation

pip install flash-attn-4

If you're on CUDA 13, install with the cu13 extra for best performance:

pip install "flash-attn-4[cu13]"

Usage

from flash_attn.cute import flash_attn_func, flash_attn_varlen_func

out = flash_attn_func(q, k, v, causal=True)

Development

git clone https://github.com/Dao-AILab/flash-attention.git
cd flash-attention
pip install -e "flash_attn/cute[dev]"       # CUDA 12.x
pip install -e "flash_attn/cute[dev,cu13]"  # CUDA 13.x (e.g. B200)
pytest tests/cute/

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

tokenspeed_fa4-4.0.0.post20260829-py3-none-any.whl (402.9 kB view details)

Uploaded Aug 29, 2026 Python 3

File details

Details for the file tokenspeed_fa4-4.0.0.post20260829-py3-none-any.whl.

File metadata

Download URL: tokenspeed_fa4-4.0.0.post20260829-py3-none-any.whl
Upload date: Aug 29, 2026
Size: 402.9 kB
Tags: Python 3
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for tokenspeed_fa4-4.0.0.post20260829-py3-none-any.whl
Algorithm	Hash digest
SHA256	`14c181f51ab2d31bd239b074f146085b5af49c3c383be12d3b84978b57ccd5ee`
MD5	`9b605e1c7be978cdd63c5496da30e25d`
BLAKE2b-256	`ca7d2f9543718d87cf55d47cb3b003140fce21718931dca701910c75583a138d`

See more details on using hashes here.

Provenance

The following attestation bundles were made for tokenspeed_fa4-4.0.0.post20260829-py3-none-any.whl:

Publisher: tokenspeed-fa4.yml on lightseekorg/tokenspeed-third-party

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: tokenspeed_fa4-4.0.0.post20260829-py3-none-any.whl
- Subject digest: 14c181f51ab2d31bd239b074f146085b5af49c3c383be12d3b84978b57ccd5ee
- Sigstore transparency entry: 2635720753
- Sigstore integration time: Aug 29, 2026
Source repository:
- Permalink: lightseekorg/tokenspeed-third-party@2d9550256e1056664d989fa7bbfbed0b8f38a3cd
- Branch / Tag: refs/heads/main
- Owner: https://github.com/lightseekorg
- Access: private
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: tokenspeed-fa4.yml@2d9550256e1056664d989fa7bbfbed0b8f38a3cd
- Trigger Event: workflow_dispatch