Super Sessions: Nodes are now automatically clustered by execution device in the background. This can improve performance in certain scenarios.
Customizable Channel Size: This allows for the creation of input data queues by publishing multiple times to the same topic.
Parallel Pipeline Runs: Added alternative method to run a pipeline called start. This allows running the pipeline and publishing data in separate threads.
Add Nodes via C-API: The C-API now fully supports the addition of nodes to a pipeline.
Breaking Changes
In previous versions there were different subscribe methods for the different tensor types but there was only one receive method. This changed and now there is only one subscribe method but there are different receive methods for each tensor type.
The C-API function pipeline_from_denkflow now takes a single pointer to the license source instead of a double pointer.