You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
PyTorch’s edge specific library is [ExecuTorch](https://github.com/pytorch/executorch/) and is designed to be lightweight, very performant even on devices with constrained hardware such as mobile phones, embedded systems and microcontrollers.
14
+
15
+
ExecuTorch relies heavily on PyTorch core technologies such as [torch.compile](https://pytorch.org/docs/stable/torch.compiler.html) and [torch.export](https://pytorch.org/docs/stable/export.html), and should be very familiar to anyone who has used PyTorch in the past.
16
+
17
+
### Getting Started
18
+
You can get started by following the [general getting started guide](https://pytorch.org/executorch/stable/getting-started.html#) or jump to the specific steps for your target device.
19
+
20
+
*[Using ExecuTorch on Android](https://pytorch.org/executorch/stable/using-executorch-android.html)
21
+
*[Using ExecuTorch on iOS](https://pytorch.org/executorch/stable/using-executorch-ios.html)
22
+
*[Using ExecuTorch with C++](https://pytorch.org/executorch/stable/using-executorch-cpp.html)
23
+
24
+
### Hardware Acceleration
25
+
ExecuTorch provides out of the box hardware acceleration for a growing number of chip manufacturers. See the following resources to learn more about how to leverage them:
0 commit comments