Closed aamirbutt closed 2 years ago
Hello @aamirbutt,
We are investigating the issue. In the mean time, could I request that you run python -m pip freeze
and include the results so that we are better able to reproduce the issue?
Regards, Taylor
FWIW, I was able to solve it by providing a custom graph-builder function:
def graph_builder(node):
if "LSTM" in node.name or node.name.startswith('prim'):
return False
else:
return True
model_neuron = torch.neuron.trace(model,
example_inputs=inputs,
strict=False,
subgraph_builder_function=graph_builder,
dynamic_batch_size=True)
closing per solution above
Hi, I am trying to test dynamic batching with pytorch. I get the following error:
Here is the full code.
My torch_neuron version: 1.9.1.2.0.392.0 Any idea what needs to be done here?