Skip to content

Fix up some Docs #10038

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 10, 2025
Merged

Fix up some Docs #10038

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/source/using-executorch-building-from-source.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ Windows (x86_64)
- Otherwise, Python's built-in virtual environment manager `python venv` is a good alternative.
* `g++` version 7 or higher, `clang++` version 5 or higher, or another
C++17-compatible toolchain.
* `python` version 3.10-3.12
* `python` version 3.10-3.12

Note that the cross-compilable core runtime code supports a wider range of
toolchains, down to C++17. See the [Runtime Overview](./runtime-overview.md) for
Expand Down Expand Up @@ -231,7 +231,7 @@ Assuming Android NDK is available, run:
mkdir cmake-android-out && cd cmake-android-out

# point -DCMAKE_TOOLCHAIN_FILE to the location where ndk is installed
cmake -DCMAKE_TOOLCHAIN_FILE=/Users/{user_name}/Library/Android/sdk/ndk/27.2.12479018/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a ..
cmake -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a ..

cd ..
cmake --build cmake-android-out -j9
Expand Down
8 changes: 4 additions & 4 deletions docs/source/using-executorch-faqs.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ if you are using Ubuntu, or use an equivalent install command.

### Missing out variants: { _ }

The model likely contains torch custom operators. Custom ops need an Executorch implementation and need to be loaded at export time. See the [ExecuTorch Custom Ops Documentation](https://pytorch.org/executorch/main/kernel-library-custom-aten-kernel.html#apis) for details on how to do this.
The model likely contains torch custom operators. Custom ops need an Executorch implementation and need to be loaded at export time. See the [ExecuTorch Custom Ops Documentation](kernel-library-custom-aten-kernel.md#apis) for details on how to do this.

### RuntimeError: PyTorch convert function for op _ not implemented

Expand All @@ -32,7 +32,7 @@ ExecuTorch error codes are defined in [executorch/core/runtime/error.h](https://

If building the runtime from source, ensure that the build is done in release mode. For CMake builds, this can be done by passing `-DCMAKE_BUILD_TYPE=Release`.

Ensure the model is delegated. If not targeting a specific accelerator, use the XNNPACK delegate for CPU performance. Undelegated operators will typically fall back to the ExecuTorch portable library, which is designed as a fallback, and is not intended for performance sensitive operators. To target XNNPACK, pass an `XnnpackPartitioner` to `to_edge_transform_and_lower`. See [Building and Running ExecuTorch with XNNPACK Backend](https://pytorch.org/executorch/main/tutorial-xnnpack-delegate-lowering.html) for more information.
Ensure the model is delegated. If not targeting a specific accelerator, use the XNNPACK delegate for CPU performance. Undelegated operators will typically fall back to the ExecuTorch portable library, which is designed as a fallback, and is not intended for performance sensitive operators. To target XNNPACK, pass an `XnnpackPartitioner` to `to_edge_transform_and_lower`. See [Building and Running ExecuTorch with XNNPACK Backend](tutorial-xnnpack-delegate-lowering.md) for more information.

Thread count can have a significant impact on CPU performance. The optimal thread count may depend on the model and application. By default, ExecuTorch will currently use as many threads as there are cores. Consider setting the thread count to cores / 2, or just set to 4 on mobile CPUs.

Expand All @@ -41,11 +41,11 @@ Thread count can be set with the following function. Ensure this is done prior t
::executorch::extension::threadpool::get_threadpool()->_unsafe_reset_threadpool(num_threads);
```

For a deeper investgiation into model performance, ExecuTorch supports operator-level performance profiling. See [Using the ExecuTorch Developer Tools to Profile a Model](https://pytorch.org/executorch/main/tutorials/devtools-integration-tutorial.html) for more information.
For a deeper investgiation into model performance, ExecuTorch supports operator-level performance profiling. See [Using the ExecuTorch Developer Tools to Profile a Model](devtools-integration-tutorial.md) for more information.

### Missing Logs

ExecuTorch provides hooks to route runtime logs. By default, logs are sent to stdout/stderr, but users can override `et_pal_emit_log_message` to route logs to a custom destination. The Android and iOS extensions also provide out-of-box log routing to the appropriate platform logs. See [Runtime Platform Abstraction Layer (PAL)](https://pytorch.org/executorch/main/runtime-platform-abstraction-layer.html) for more information.
ExecuTorch provides hooks to route runtime logs. By default, logs are sent to stdout/stderr, but users can override `et_pal_emit_log_message` to route logs to a custom destination. The Android and iOS extensions also provide out-of-box log routing to the appropriate platform logs. See [Runtime Platform Abstraction Layer (PAL)](runtime-platform-abstraction-layer.md) for more information.

### Error setting input: 0x10 / Attempted to resize a bounded tensor...

Expand Down
Loading