Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/MachineLearningSystem/hidet
Hidet: A compilation-based DNN inference framework
https://github.com/MachineLearningSystem/hidet
Last synced: 9 days ago
JSON representation
Hidet: A compilation-based DNN inference framework
- Host: GitHub
- URL: https://github.com/MachineLearningSystem/hidet
- Owner: MachineLearningSystem
- License: apache-2.0
- Fork: true (hidet-org/hidet)
- Created: 2023-01-16T01:53:08.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-01-14T21:41:59.000Z (almost 2 years ago)
- Last Synced: 2024-08-02T19:34:02.338Z (4 months ago)
- Homepage:
- Size: 2.15 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-AI-system - Hidet: Task Mapping Programming Paradigm for Deep Learning Tensor Programs ASPLOS'23
README
# Hidet: A compilation-based deep learning framework
[**Documentation**](http://docs.hidet.org/)
Hidet is an open-source DNN inference framework based on compilation.
It supports end-to-end compilation of DNN models from PyTorch and ONNX to efficient cuda kernels.
A series of graph-level and operator-level optimizations are applied to optimize the performance.
## Getting Started
### Installation
```bash
pip install hidet
```
See [here](http://docs.hidet.org/) for building from source.
### Usage
Optimize a PyTorch model through hidet (require PyTorch 2.0):
```python
import torch
import hidet
# Register hidet backends for pytorch dynamo, can be omitted if you import torch before hidet
hidet.torch.register_dynamo_backends()
# Define pytorch model
model = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).cuda().eval()
x = torch.rand(1, 3, 224, 224).cuda()
# Compile the model through Hidet
model_opt = torch.compile(model, backend='hidet')
# Run the optimized model
y = model_opt(x)
```
See the following tutorials to learn other usgae:
- [Quick Start](http://docs.hidet.org/stable/gallery/getting-started/quick-start.html)
- [Optimize PyTorch models](http://docs.hidet.org/stable/gallery/tutorials/optimize-pytorch-model.html)
- [Optimize ONNX models](http://docs.hidet.org/stable/gallery/tutorials/run-onnx-model.html)
## Publication
Hidet originates from the following research work. If you used **Hidet** in your research, welcome to cite our
[paper](https://arxiv.org/abs/2210.09603).
- **Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs.**
Yaoyao Ding, Cody Hao Yu, Bojian Zheng, Yizhi Liu, Yida Wang, and Gennady Pekhimenko.
## Development
Hidet is currently under active development by a team at [CentML Inc](https://centml.ai/).
## Contributing
We welcome contributions from the community. Please see
[contribution guide](https://docs.hidet.org/stable/developer-guides/contributing.html)
for more details.
## License
Hidet is released under the [Apache 2.0 license](LICENSE).