When I run the openai whisper example from the DJL demo, on a GPU, I'm getting this error:
Caused by: ai.djl.engine.EngineException: Method 'forward' is not defined.
at ai.djl.pytorch.jni.PyTorchLibrary.moduleRunMethod(Native Method)
at ai.djl.pytorch.jni.IValueUtils.forward(IValueUtils.java:55)
at ai.djl.pytorch.engine.PtSymbolBlock.forwardInternal(PtSymbolBlock.java:145)
at ai.djl.nn.AbstractBaseBlock.forward(AbstractBaseBlock.java:79)
at ai.djl.nn.Block.forward(Block.java:127)
at ai.djl.inference.Predictor.predictInternal(Predictor.java:144)
at ai.djl.inference.Predictor.batchPredict(Predictor.java:171)
... 13 common frames omitted
I read that this could be from JIT of PyTorch Engine. However I could not find a example/docs on how JIT could be switched of from DJL java code.
Is this due to some timed out usage ? How can I get around this exception?
