kernel-fun
CuTe/Triton kernels for linear-attention ops (KDA chunk kernel, KDA short conv), as drop-in replacements for flash-linear-attention. Release artifact of allenai/kernel-fun-dev.
View on Github
Activity
- Latest release
- 4d ago
- Total releases
- 2
- Cadence
- ~daily
- Last 12 months
- 2
Reach
- Stars
- 0
Details
- License
- Apache-2.0
- First release
- Sep 11, 2026
Releases
| Version | Released | |
|---|---|---|
0.2.0
initial
| ||
0.2.0.dev1
pre
|