Instructions to use sigmoid-neuron/flash-attention-1-triton with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use sigmoid-neuron/flash-attention-1-triton with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("sigmoid-neuron/flash-attention-1-triton", version=1) - Notebooks
- Google Colab
- Kaggle
Commit History
-
feat: add support for ROCm backend and update device validation for HIP and XPU compatibility
a391959 -
feat: implement Flash Attention 1 using Triton with PyTorch C++ bindings and test suite
8cf888e