flash-attn-4
Flash Attention CUTE (CUDA Template Engine) implementation
- Latest release
- Jun 03, 2026
- Releases
- 14
- Known CVEs
- 0
- First release
- Feb 09, 2026
- License
- unknown
Repository
Source
- Stars
- —
- Forks
- —
- Open issues
- —
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
Insights
Activity
- Total releases
- 14
- Last 12 months
- 14
- Cadence
- ~7 days
- Dependencies
- 10
Releases per month
last 12 monthsRelease mix
- pre 13
14
releases
Dependencies
Depends on
4.0.0b16-
apache-tvm-ffi <0.2,>=0.1.5
-
einops
-
nvidia-cutlass-dsl >=4.5.2
-
pytest
-
pytest-xdist
-
quack-kernels >=0.5.0
-
ruff
-
torch
-
torch-c-dlpack-ext
-
typing-extensions
Used by
3Releases
| Version | Released | |
|---|---|---|
4.0.0b16
pre
| ||
4.0.0b15
pre
| ||
4.0.0b14
pre
| ||
4.0.0b13
pre
| ||
4.0.0b12
pre
| ||
4.0.0b11
pre
| ||
4.0.0b10
pre
| ||
4.0.0b9
pre
| ||
4.0.0b8
pre
| ||
4.0.0b7
pre
| ||
4.0.0b5
pre
| ||
4.0.0b4
pre
| ||
4.0.0b3
pre
| ||
0.0.1
initial
|