android litert -fregister-allocation=64 bug

[sungerk]

Process: com.geenk.zto.sys, PID: 13270
java.lang.RuntimeException: java.lang.IllegalArgumentException: Internal error: Failed to apply delegate: Failed to build program executable - Invalid build optionserror: unknown build option '-fregister-allocation=64'

                                                                                                Falling back to OpenGL
                                                                                                TfLiteGpuDelegate Init: No shader implementation for transpose
                                                                                                TfLiteGpuDelegate Prepare: delegate is not initialized
                                                                                                Node number 257 (TfLiteGpuDelegateV2) failed to prepare.
                                                                                                Restored original execution plan after delegate application failure.
                                                                                                	at com.zto.ai.machine_vision.c.d(Detector.java:41)
                                                                                                	at c1.a.a(DetectPackage.java:10)

mobile phone :PBBM00 Android 9

implementation("com.google.ai.edge.litert:litert-support:1.0.1")
implementation("com.google.ai.edge.litert:litert-gpu:1.0.1")
implementation("com.google.ai.edge.litert:litert-gpu-api:1.0.1")
implementation("com.google.ai.edge.litert:litert-metadata:1.0.1")

this is my code
`
public void init(Context context, String modelPath) {
CompatibilityList compatList = new CompatibilityList();
Interpreter.Options options = new Interpreter.Options();
if (compatList.isDelegateSupportedOnThisDevice()) {
options.setUseNNAPI(true);
GpuDelegate delegate = new GpuDelegate(compatList.getBestOptionsForThisDevice());
options.addDelegate(delegate);
} else {
options.setUseXNNPACK(true);
options.setNumThreads(4);
}
try {
MappedByteBuffer mappedByteBuffer = FileUtil.loadMappedFile(context, modelPath);
this.interpreter = new Interpreter(mappedByteBuffer, options);
initializeTensorShapes();
} catch (Exception e) {
throw new RuntimeException(e);
}
}

[pkgoogle]

Hi @sungerk, what model are you using?