Fix XNNPACK code snippet rendering (#19685)

This commit is contained in:
Nat Kershaw (MSFT) 2024-02-27 19:47:29 -08:00 committed by GitHub
parent e74b8e6050
commit 401a08884e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -28,7 +28,7 @@ See [here](../install/index.md#install-on-ios) for installation instructions.
Please see the [Build page](../build/eps.md#xnnpack) for instructions on building a package that includes the XNNPACK EP.
Support build for Android/iOS/Windows/Linux
You can build ONNX Runtime with the XNNPACK EP for Android, iOS, Windows, and Linux.
## Usage
@ -41,7 +41,7 @@ The XNNPACK EP must be explicitly registered when creating the inference session
```C++
Ort::Env env = Ort::Env{ORT_LOGGING_LEVEL_ERROR, "Default"};
Ort::SessionOptions so;
so.AppendExecutionProvider("XNNPACK", {{"intra_op_num_threads", std::to_string(intra_op_num_threads)}});
so.AppendExecutionProvider("XNNPACK", {"intra_op_num_threads", std::to_string(intra_op_num_threads)});
Ort::Session session(env, model_path, so);
```
@ -56,7 +56,7 @@ To minimize this, we recommend setting the following options:
```
2. Set the XNNPACK intra-op thread-pool size when registering the XNNPACK EP. The suggested value would be the number of physical cores on the device.
```C++
so.AppendExecutionProvider("XNNPACK", {{"intra_op_num_threads", std::to_string(intra_op_num_threads)}});
so.AppendExecutionProvider("XNNPACK", {"intra_op_num_threads", std::to_string(intra_op_num_threads)});
```
3. Set the ORT intra-op thread-pool size to 1:
```C++