From c1685b8ee382ccf8900ae565c062b26cd4246f21 Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Thu, 13 Mar 2025 18:04:48 -0400 Subject: [PATCH 1/9] Updating ExecuTorch getting started page. --- _get_started/mobile.md | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 2a640293144c..185965b5bd83 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -1,6 +1,6 @@ --- layout: get_started -title: ExecuTorch +title: PyTorch for Edge permalink: /get-started/executorch/ background-class: get-started-background body-class: get-started @@ -10,11 +10,29 @@ published: true ## Get Started with PyTorch ExecuTorch -

- - ExecuTorch Documentation - -

+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. + +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/main/export.html), and should be very familiar with anyone who has used PyTorch in the past. + +### Getting Started +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. + +[Using ExecuTorch on Android](https://pytorch.org/executorch/stable/using-executorch-android.html) +[Using ExecuTorch on iOS](https://pytorch.org/executorch/stable/using-executorch-ios.html) +[Using ExecuTorch with C++](https://pytorch.org/executorch/stable/using-executorch-cpp.html) + +### Hardware Acceleration +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. + +[Backend Overview](https://pytorch.org/executorch/stable/backends-overview.html) +[XNNPACK](https://pytorch.org/executorch/stable/backends-xnnpack.html) +[Core ML](https://pytorch.org/executorch/stable/backends-coreml.html) +[MPS](https://pytorch.org/executorch/stable/backends-mps.html) +[Vulkan](https://pytorch.org/executorch/stable/backends-vulkan.html) +[ARM Ethos-U](https://pytorch.org/executorch/stable/backends-arm-ethos-u.html) +[Qualcomm AI Engine](https://pytorch.org/executorch/stable/backends-qualcomm.html) +[MediaTek](https://pytorch.org/executorch/stable/backends-mediatek.html) +[Cadence Xtensa](https://pytorch.org/executorch/main/backends-cadence.html) From ec5be8b7cd30ce9c628c1d4dd3da75bda345e49a Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Fri, 14 Mar 2025 16:22:47 -0400 Subject: [PATCH 2/9] Update _get_started/mobile.md Co-authored-by: Svetlana Karslioglu --- _get_started/mobile.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 185965b5bd83..880cc4543141 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -10,7 +10,7 @@ published: true ## Get Started with PyTorch ExecuTorch -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. +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. 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/main/export.html), and should be very familiar with anyone who has used PyTorch in the past. From 104588aae5d548e9b722072647e3d9a5ccb8ee9e Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Fri, 14 Mar 2025 16:22:54 -0400 Subject: [PATCH 3/9] Update _get_started/mobile.md Co-authored-by: Svetlana Karslioglu --- _get_started/mobile.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 880cc4543141..326223f2581d 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -12,7 +12,7 @@ published: true 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. -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/main/export.html), and should be very familiar with anyone who has used PyTorch in the past. +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/main/export.html), and should be very familiar to anyone who has used PyTorch in the past. ### Getting Started 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. From bd43244c775595fbb6c359fde15981a79dfcb6bd Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Fri, 14 Mar 2025 16:23:01 -0400 Subject: [PATCH 4/9] Update _get_started/mobile.md Co-authored-by: Svetlana Karslioglu --- _get_started/mobile.md | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 326223f2581d..4f47883ad3ad 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -24,15 +24,15 @@ You can get started by following the [general getting started guide](https://pyt ### Hardware Acceleration 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. -[Backend Overview](https://pytorch.org/executorch/stable/backends-overview.html) -[XNNPACK](https://pytorch.org/executorch/stable/backends-xnnpack.html) -[Core ML](https://pytorch.org/executorch/stable/backends-coreml.html) -[MPS](https://pytorch.org/executorch/stable/backends-mps.html) -[Vulkan](https://pytorch.org/executorch/stable/backends-vulkan.html) -[ARM Ethos-U](https://pytorch.org/executorch/stable/backends-arm-ethos-u.html) -[Qualcomm AI Engine](https://pytorch.org/executorch/stable/backends-qualcomm.html) -[MediaTek](https://pytorch.org/executorch/stable/backends-mediatek.html) -[Cadence Xtensa](https://pytorch.org/executorch/main/backends-cadence.html) +* [Backend Overview](https://pytorch.org/executorch/stable/backends-overview.html) +* [XNNPACK](https://pytorch.org/executorch/stable/backends-xnnpack.html) +* [Core ML](https://pytorch.org/executorch/stable/backends-coreml.html) +* [MPS](https://pytorch.org/executorch/stable/backends-mps.html) +* [Vulkan](https://pytorch.org/executorch/stable/backends-vulkan.html) +* [ARM Ethos-U](https://pytorch.org/executorch/stable/backends-arm-ethos-u.html) +* [Qualcomm AI Engine](https://pytorch.org/executorch/stable/backends-qualcomm.html) +* [MediaTek](https://pytorch.org/executorch/stable/backends-mediatek.html) +* [Cadence Xtensa](https://pytorch.org/executorch/main/backends-cadence.html) From 99379b24734ab592046d5d94314f92c193a1b5b5 Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Fri, 14 Mar 2025 16:23:07 -0400 Subject: [PATCH 5/9] Update _get_started/mobile.md Co-authored-by: Svetlana Karslioglu --- _get_started/mobile.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 4f47883ad3ad..0cf33c519419 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -22,7 +22,7 @@ You can get started by following the [general getting started guide](https://pyt [Using ExecuTorch with C++](https://pytorch.org/executorch/stable/using-executorch-cpp.html) ### Hardware Acceleration -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. +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: * [Backend Overview](https://pytorch.org/executorch/stable/backends-overview.html) * [XNNPACK](https://pytorch.org/executorch/stable/backends-xnnpack.html) From 15a8784eb1e0b0b6762bd882eb979a16c44f750b Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Fri, 14 Mar 2025 16:23:15 -0400 Subject: [PATCH 6/9] Update _get_started/mobile.md Co-authored-by: Svetlana Karslioglu --- _get_started/mobile.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 0cf33c519419..e1452f8a97cd 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -17,9 +17,9 @@ ExecuTorch relies heavily on PyTorch core technologies such as [torch.compile](h ### Getting Started 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. -[Using ExecuTorch on Android](https://pytorch.org/executorch/stable/using-executorch-android.html) -[Using ExecuTorch on iOS](https://pytorch.org/executorch/stable/using-executorch-ios.html) -[Using ExecuTorch with C++](https://pytorch.org/executorch/stable/using-executorch-cpp.html) +* [Using ExecuTorch on Android](https://pytorch.org/executorch/stable/using-executorch-android.html) +* [Using ExecuTorch on iOS](https://pytorch.org/executorch/stable/using-executorch-ios.html) +* [Using ExecuTorch with C++](https://pytorch.org/executorch/stable/using-executorch-cpp.html) ### Hardware Acceleration 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: From 4cba4568b9e3ffda9e413ef0e6df0a35f56df7cf Mon Sep 17 00:00:00 2001 From: Svetlana Karslioglu Date: Mon, 17 Mar 2025 10:26:37 -0700 Subject: [PATCH 7/9] Update _get_started/mobile.md --- _get_started/mobile.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index e1452f8a97cd..79dcbf80e219 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -10,7 +10,7 @@ published: true ## Get Started with PyTorch ExecuTorch -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. +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. 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/main/export.html), and should be very familiar to anyone who has used PyTorch in the past. From 7715b373466bf160878ba6d5a06790acc3c70d52 Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Tue, 18 Mar 2025 15:03:22 -0400 Subject: [PATCH 8/9] Fixing link. --- _get_started/mobile.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 79dcbf80e219..46121d022d3c 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -12,7 +12,7 @@ published: true 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. -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/main/export.html), and should be very familiar to anyone who has used PyTorch in the past. +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. ### Getting Started 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. From 699579eadec97519e4ba3de6593d72f6b60f6afb Mon Sep 17 00:00:00 2001 From: Alanna Burke Date: Tue, 18 Mar 2025 15:05:41 -0400 Subject: [PATCH 9/9] Fixing link. --- _get_started/mobile.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_get_started/mobile.md b/_get_started/mobile.md index 46121d022d3c..d709ee61e2f8 100644 --- a/_get_started/mobile.md +++ b/_get_started/mobile.md @@ -32,7 +32,7 @@ ExecuTorch provides out of the box hardware acceleration for a growing number of * [ARM Ethos-U](https://pytorch.org/executorch/stable/backends-arm-ethos-u.html) * [Qualcomm AI Engine](https://pytorch.org/executorch/stable/backends-qualcomm.html) * [MediaTek](https://pytorch.org/executorch/stable/backends-mediatek.html) -* [Cadence Xtensa](https://pytorch.org/executorch/main/backends-cadence.html) +* [Cadence Xtensa](https://pytorch.org/executorch/stable/backends-cadence.html)