Closed LEECHOONGHO closed 1 year ago
In the multiscale-retention`s recurrent forward, it looks like the incremental state is not being updated(not returned)[1].
[1]https://github.com/microsoft/torchscale/blob/258eda33083f6361e7305f2a5afd241e381826e1/torchscale/component/multiscale_retention.py#L117C18-L117C18
The incremental state is a Python dictionary, so it's updated in place.
Oh I see. sorry for my mistake.
In the multiscale-retention`s recurrent forward, it looks like the incremental state is not being updated(not returned)[1].
[1]https://github.com/microsoft/torchscale/blob/258eda33083f6361e7305f2a5afd241e381826e1/torchscale/component/multiscale_retention.py#L117C18-L117C18