{"id":13436553,"url":"https://github.com/pytorch/executorch","last_synced_at":"2025-05-11T03:49:01.384Z","repository":{"id":200803186,"uuid":"463628495","full_name":"pytorch/executorch","owner":"pytorch","description":"On-device AI across mobile, embedded and edge for PyTorch","archived":false,"fork":false,"pushed_at":"2025-05-11T03:39:21.000Z","size":201792,"stargazers_count":2825,"open_issues_count":1085,"forks_count":537,"subscribers_count":68,"default_branch":"main","last_synced_at":"2025-05-11T03:48:38.276Z","etag":null,"topics":["deep-learning","embedded","gpu","machine-learning","mobile","neural-network","tensor"],"latest_commit_sha":null,"homepage":"https://pytorch.org/executorch/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pytorch.png","metadata":{"files":{"readme":"README-wheel.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-02-25T17:58:31.000Z","updated_at":"2025-05-10T14:36:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"a93289b5-4f89-4db5-835f-1b0897829419","html_url":"https://github.com/pytorch/executorch","commit_stats":{"total_commits":4068,"total_committers":234,"mean_commits":"17.384615384615383","dds":0.94960668633235,"last_synced_commit":"df72b8cd9d93ef61022067c89d30b062ab7a28fa"},"previous_names":["pytorch/executorch"],"tags_count":313,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pytorch%2Fexecutorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pytorch%2Fexecutorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pytorch%2Fexecutorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pytorch%2Fexecutorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pytorch","download_url":"https://codeload.github.com/pytorch/executorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253514559,"owners_count":21920334,"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":["deep-learning","embedded","gpu","machine-learning","mobile","neural-network","tensor"],"created_at":"2024-07-31T03:00:49.966Z","updated_at":"2025-05-11T03:49:01.366Z","avatar_url":"https://github.com/pytorch.png","language":"Python","readme":"**ExecuTorch** is a [PyTorch](https://pytorch.org/) platform that provides\ninfrastructure to run PyTorch programs everywhere from AR/VR wearables to\nstandard on-device iOS and Android mobile deployments. One of the main goals for\nExecuTorch is to enable wider customization and deployment capabilities of the\nPyTorch programs.\n\nThe `executorch` pip package is in beta.\n* Supported python versions: 3.10, 3.11, 3.12\n* Compatible systems: Linux x86_64, macOS aarch64\n\nThe prebuilt `executorch.runtime` module included in this package provides a way\nto run ExecuTorch `.pte` files, with some restrictions:\n* Only [core ATen operators](docs/source/ir-ops-set-definition.md) are linked into the prebuilt module\n* Only the [XNNPACK backend delegate](docs/source/backends-xnnpack.md) is linked into the prebuilt module.\n* \\[macOS only] [Core ML](docs/source/backends-coreml.md) and [MPS](docs/source/backends-mps.md) backend\n  are also linked into the prebuilt module.\n\nPlease visit the [ExecuTorch website](https://pytorch.org/executorch) for\ntutorials and documentation. Here are some starting points:\n* [Getting Started](https://pytorch.org/executorch/main/getting-started-setup)\n  * Set up the ExecuTorch environment and run PyTorch models locally.\n* [Working with local LLMs](docs/source/llm/getting-started.md)\n  * Learn how to use ExecuTorch to export and accelerate a large-language model\n    from scratch.\n* [Exporting to ExecuTorch](https://pytorch.org/executorch/main/tutorials/export-to-executorch-tutorial)\n  * Learn the fundamentals of exporting a PyTorch `nn.Module` to ExecuTorch, and\n    optimizing its performance using quantization and hardware delegation.\n* Running LLaMA on [iOS](docs/source/llm/llama-demo-ios.md) and [Android](docs/source/llm/llama-demo-android.md) devices.\n  * Build and run LLaMA in a demo mobile app, and learn how to integrate models\n    with your own apps.\n","funding_links":[],"categories":["Python","Tools, SDKs, and Compilers","Hardware Acceleration and Deployment Strategies","Edge and Retro Inference","Repos","其他_机器学习与深度学习","📋 Contents","Infrastructure / Deployment of LLMs on Device","📱 Edge \u0026 On-Device AI"],"sub_categories":["Popular On-Device LLMs Framework","🧩 11. Specialized Domains","Deployment Frameworks","Notable MCP Servers"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpytorch%2Fexecutorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpytorch%2Fexecutorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpytorch%2Fexecutorch/lists"}