Package profile
kernel-fun
- Summary: CuTe/Triton kernels for linear-attention ops (KDA chunk kernel, KDA short conv), as drop-in replacements for flash-linear-attention, on Blackwell
- Author: Allen Institute for AI
- License: Apache-2.0
- Source: https://github.com/allenai/kernel-fun
- Number of releases: 2
- First release: 0.2.0.dev1 on 2026-09-11
- Latest release: 0.2.0 on 2026-09-11
- Latest release size: 117.8 KB (pure Python wheel)