Make the number of ensemble members internal to the Aurora model.

Aurora 1.5 Ensemble has the option of being based on an ensemble with N members. This is currently achieved by running the model N times in the context in which the ensemble approach is required.

There should be an option to make the ensemble members internal to Aurora, so that getting all of the ensemble results is done using a single call to e.g. forward, as opposed to running N of them in a loop.

This would expose more opportunities for making the full use of GPUs. Currently, each ensemble member is a completely separate model with separate inputs and outputs. This means that a high-performance GPU may be under-utilised compared to representing all ensemble members using the same tensor.

Start by tracing the Aurora 1.5 Ensemble model and its forward entry point to understand how ensemble members are currently invoked. Confirm how inputs and outputs are represented across the existing repeated calls, then define the internal ensemble interface. Done means one forward call returns all ensemble results while enabling the members to use the GPU more fully.