Update README regarding Metal delegate instructions.
PiperOrigin-RevId: 320880762
Change-Id: I6b36930f9b946b1f798c335326af182be49fedb2
diff --git a/tensorflow/lite/delegates/gpu/README.md b/tensorflow/lite/delegates/gpu/README.md
index 552e1cd..c37ee90 100644
--- a/tensorflow/lite/delegates/gpu/README.md
+++ b/tensorflow/lite/delegates/gpu/README.md
@@ -51,6 +51,10 @@
## Basic Usage
+**Note:** Following section describes the example usage for Android GPU delegate
+with C++. For other languages and platforms, please see
+[the documentation](https://www.tensorflow.org/lite/performance/gpu).
+
Using TFLite on GPU is as simple as getting the GPU delegate via
`TfLiteGpuDelegateV2Create()` and then passing it to
`Interpreter::ModifyGraphWithDelegate()` instead of calling
@@ -99,13 +103,13 @@
compilation flags should look like:
```sh
-bazel build --config ios_arm64 //path/to/your:project
+bazel build --config ios_fat //path/to/your:project
```
## Advanced Usage: Delegate Options
There are GPU options that can be set and passed on to
-`TfLiteGpuDelegateCreate()`. When option is set to `nullptr` as shown in the
+`TfLiteGpuDelegateV2Create()`. When option is set to `nullptr` as shown in the
Basic Usage, it translates to:
```c++
@@ -113,12 +117,13 @@
TfLiteGpuDelegateOptionsV2Default();
```
-Similar for `NewTfLiteMetalDelegate()`:
+Similar for `TFLGpuDelegateCreate()`:
```c++
-const TfLiteMetalDelegateOptions kDefaultOptions = {
- .precision_loss_allowed = 0, // false
- .wait_type = TFLITE_METAL_WAIT_TYPE_SLEEP,
+const TFLGpuDelegateOptions kDefaultOptions = {
+ .allow_precision_loss = false,
+ .wait_type = TFLGpuDelegateWaitTypePassive,
+ .enable_quantization = false,
};
```
@@ -126,9 +131,10 @@
set the options to avoid any unexpected artifacts in case default values are
changed.
-*IMPORTANT:* Note that the default option does not allow precision loss, and
-thus may not be the fastest. For faster execution, you may want to set
-`precision_loss_allowed` to `1` for FP16 execution.
+*IMPORTANT:* Note that the default option may not be the fastest. For faster
+execution, you may want to set `allow_precision_loss` to `true` so that the GPU
+performs FP16 calculation internally, and set `wait_type` to
+`TFLGpuDelegateWaitTypeAggressive` to avoid GPU sleep mode.
## Tips and Tricks
