template / README.md
meatballhat-replicate's picture
Duplicate from kernels-community/template
4fbc4c4
|
Raw
History Blame Contribute Delete
855 Bytes
> [!CAUTION]
> Starting from September 13, 2026, we will be removing the "model" type repositories of kernels (e.g., kernels-community/flash-attn3). Make sure you're using a latest version of kernels. If you face any disruption, please report them here: https://github.com/huggingface/kernels/issues/new.
# __KERNEL_NAME__
A custom kernel for PyTorch.
## Installation
```bash
pip install __REPO_ID__
```
## Usage
```python
import torch
from __KERNEL_NAME_NORMALIZED__ import __KERNEL_NAME_NORMALIZED__
# Create input tensor
x = torch.randn(1024, 1024, device="cuda")
# Run kernel
result = __KERNEL_NAME_NORMALIZED__(x)
```
## Development
### Building
```bash
nix develop
nix run .#build-and-copy
```
### Testing
```bash
nix develop .#test
pytest tests/
```
### Test as a `kernels` user
```bash
uv run example.py
```
## License
Apache 2.0