TensorRT Plugin: If the dynamic output shape can only be determined after the computation of the plugin, how to handle this case?

Does tensorRT have a plan to support the situation where the output dimension is not known until the plugin is calculated? Now encountering this kind of problem, how can I solve it? Thanks a lot!

Please refer to below links related custom plugin implementation and sample:

While IPluginV2 and IPluginV2Ext interfaces are still supported for backward compatibility with TensorRT 5.1 and 6.0.x respectively, however, we recommend that you write new plugins or refactor existing ones to target the IPluginV2DynamicExt or IPluginV2IOExt interfaces instead.