{"id":13604374,"url":"https://github.com/MachineLearningSystem/hidet","last_synced_at":"2025-04-12T02:30:34.440Z","repository":{"id":185461799,"uuid":"589393439","full_name":"MachineLearningSystem/hidet","owner":"MachineLearningSystem","description":"Hidet: A compilation-based DNN inference framework","archived":false,"fork":true,"pushed_at":"2023-01-14T21:41:59.000Z","size":2253,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2024-08-02T19:34:02.338Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"hidet-org/hidet","license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MachineLearningSystem.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-01-16T01:53:08.000Z","updated_at":"2023-01-15T15:34:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"ae344904-080a-415e-91c4-4f8569ce31d2","html_url":"https://github.com/MachineLearningSystem/hidet","commit_stats":null,"previous_names":["machinelearningsystem/hidet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MachineLearningSystem%2Fhidet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MachineLearningSystem%2Fhidet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MachineLearningSystem%2Fhidet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MachineLearningSystem%2Fhidet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MachineLearningSystem","download_url":"https://codeload.github.com/MachineLearningSystem/hidet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223489526,"owners_count":17153776,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T19:00:44.456Z","updated_at":"2024-11-07T09:30:17.210Z","avatar_url":"https://github.com/MachineLearningSystem.png","language":null,"readme":"# Hidet: A compilation-based deep learning framework\n[**Documentation**](http://docs.hidet.org/) \n\n![GitHub](https://img.shields.io/github/license/hidet-org/hidet)\n![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/hidet-org/hidet/tests.yaml)\n\n\nHidet is an open-source DNN inference framework based on compilation. \nIt supports end-to-end compilation of DNN models from PyTorch and ONNX to efficient cuda kernels.\nA series of graph-level and operator-level optimizations are applied to optimize the performance.\n\n## Getting Started\n\n### Installation\n```bash\npip install hidet\n```\nSee [here](http://docs.hidet.org/) for building from source.\n\n### Usage\n\nOptimize a PyTorch model through hidet (require PyTorch 2.0):\n```python\nimport torch\nimport hidet\n\n# Register hidet backends for pytorch dynamo, can be omitted if you import torch before hidet\nhidet.torch.register_dynamo_backends()  \n\n# Define pytorch model\nmodel = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).cuda().eval()\nx = torch.rand(1, 3, 224, 224).cuda()\n\n# Compile the model through Hidet\nmodel_opt = torch.compile(model, backend='hidet')  \n\n# Run the optimized model\ny = model_opt(x)\n```\nSee the following tutorials to learn other usgae:\n- [Quick Start](http://docs.hidet.org/stable/gallery/getting-started/quick-start.html)\n- [Optimize PyTorch models](http://docs.hidet.org/stable/gallery/tutorials/optimize-pytorch-model.html)\n- [Optimize ONNX models](http://docs.hidet.org/stable/gallery/tutorials/run-onnx-model.html)\n\n## Publication\nHidet originates from the following research work. If you used **Hidet** in your research, welcome to cite our\n[paper](https://arxiv.org/abs/2210.09603). \n\n- **Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs.**  \n  Yaoyao Ding, Cody Hao Yu, Bojian Zheng, Yizhi Liu, Yida Wang, and Gennady Pekhimenko. \n\n## Development \nHidet is currently under active development by a team at [CentML Inc](https://centml.ai/). \n\n## Contributing\nWe welcome contributions from the community. Please see \n[contribution guide](https://docs.hidet.org/stable/developer-guides/contributing.html)\nfor more details.\n\n## License\nHidet is released under the [Apache 2.0 license](LICENSE).\n","funding_links":[],"categories":["Paper-Code"],"sub_categories":["Optimization"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMachineLearningSystem%2Fhidet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMachineLearningSystem%2Fhidet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMachineLearningSystem%2Fhidet/lists"}