This release is a pre-release and may not be stable for production use.
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 Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file flash_attn_4-4.0.0b24.tar.gz.
File metadata
- Download URL: flash_attn_4-4.0.0b24.tar.gz
- Upload date:
- Size: 358.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6c4b981ef433882871ded48317deaa18ea22f731ca4f8b9387804bfa2e8078e2
|
|
| MD5 |
b2820956e7d7c9fe3195985d556f11f0
|
|
| BLAKE2b-256 |
32741303dfd7a38d91c0e9717c8367b30cdf6d249fb1a42feabceeda1ed86fbf
|
Provenance
The following attestation bundles were made for flash_attn_4-4.0.0b24.tar.gz:
Publisher:
publish-fa4.yml on Dao-AILab/flash-attention
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
flash_attn_4-4.0.0b24.tar.gz -
Subject digest:
6c4b981ef433882871ded48317deaa18ea22f731ca4f8b9387804bfa2e8078e2 - Sigstore transparency entry: 2280097750
- Sigstore integration time:
-
Permalink:
Dao-AILab/flash-attention@849f660f73b176e5ad5670e7f822c7fa9f3eaf8b -
Branch / Tag:
refs/heads/main - Owner: https://github.com/Dao-AILab
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-fa4.yml@849f660f73b176e5ad5670e7f822c7fa9f3eaf8b -
Trigger Event:
schedule
-
Statement type:
File details
Details for the file flash_attn_4-4.0.0b24-py3-none-any.whl.
File metadata
- Download URL: flash_attn_4-4.0.0b24-py3-none-any.whl
- Upload date:
- Size: 383.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c1dcf0dfcf37c4496728547dcb3c1e66d7dcaa07cfedef0f26ccc4d74453951f
|
|
| MD5 |
126106ab521e972c13629d4392580e12
|
|
| BLAKE2b-256 |
e582861caf5303cde9ba1499904d63be94b1464a4c0932215f2e77500e5387ab
|
Provenance
The following attestation bundles were made for flash_attn_4-4.0.0b24-py3-none-any.whl:
Publisher:
publish-fa4.yml on Dao-AILab/flash-attention
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
flash_attn_4-4.0.0b24-py3-none-any.whl -
Subject digest:
c1dcf0dfcf37c4496728547dcb3c1e66d7dcaa07cfedef0f26ccc4d74453951f - Sigstore transparency entry: 2280097843
- Sigstore integration time:
-
Permalink:
Dao-AILab/flash-attention@849f660f73b176e5ad5670e7f822c7fa9f3eaf8b -
Branch / Tag:
refs/heads/main - Owner: https://github.com/Dao-AILab
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-fa4.yml@849f660f73b176e5ad5670e7f822c7fa9f3eaf8b -
Trigger Event:
schedule
-
Statement type:
