Skip to content

Update README.md #8868

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.

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
Mar 1, 2025
Merged
Changes from all commits
Commits
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
42 changes: 3 additions & 39 deletions extension/benchmark/apple/Benchmark/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,47 +30,11 @@ cd executorch

This command performs a shallow clone to speed up the process.

### Set Up the Frameworks
### Build the Frameworks

The Benchmark App relies on prebuilt ExecuTorch frameworks.
You have two options:
The Benchmark App is configured to use a Swift PM package that provides the prebuilt ExecuTorch frameworks.

<details>
<summary>Option 1: Download Prebuilt Frameworks</summary>
<br/>

Run the provided script to download the prebuilt frameworks:

```bash
./extension/benchmark/apple/Benchmark/Frameworks/download_frameworks.sh
```
</details>

<details>
<summary>Option 2: Build Frameworks Locally</summary>
<br/>

Alternatively, you can build the frameworks yourself by following the [guide](https://pytorch.org/executorch/main/apple-runtime.html#local-build).
</details>

Once the frameworks are downloaded or built, verify that the `Frameworks` directory contains the necessary `.xcframework` files:

```bash
ls extension/benchmark/apple/Benchmark/Frameworks
```

You should see:

```
backend_coreml.xcframework
backend_mps.xcframework
backend_xnnpack.xcframework
executorch.xcframework
kernels_custom.xcframework
kernels_optimized.xcframework
kernels_portable.xcframework
kernels_quantized.xcframework
```
By default, the app relies on the package referencing locally built binaries. To ensure it functions correctly, you must first build the frameworks by following the [guide](https://pytorch.org/executorch/main/using-executorch-ios.html#building-from-source).

## Adding Models and Resources

Expand Down
Loading