Instructions to use kernels-community/flash-attn-ops with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use kernels-community/flash-attn-ops with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("kernels-community/flash-attn-ops") - Notebooks
- Google Colab
- Kaggle
| library_name: kernels | |
| license: bsd-3-clause | |
| This is the repository card of kernels-community/flash-attn-ops that has been pushed on the Hub. It was built to be used with the [`kernels` library](https://github.com/huggingface/kernels). This card was automatically generated. | |
| ## How to use | |
| ```python | |
| # make sure `kernels` is installed: `pip install -U kernels` | |
| from kernels import get_kernel | |
| kernel_module = get_kernel("kernels-community/flash-attn-ops") | |
| cross_entropy_loss = kernel_module.cross_entropy_loss | |
| cross_entropy_loss(...) | |
| ``` | |
| ## Available functions | |
| - `cross_entropy_loss` | |
| - `CrossEntropyLoss` | |
| - `apply_rotary` | |
| - `layer_norm_fn` | |
| - `rms_norm_fn` | |
| - `layer_norm_linear_fn` | |
| - `LayerNormFn` | |
| - `RMSNorm` | |
| ## Benchmarks | |
| No benchmark available yet. | |