Add generic KV caching support, use it with Whisper

[katalinic-gc]

What does this PR do?

Intended usage for Whisper:

pipelined_model = pipelined_model.parallelize(
    for_generation=True, use_cache=use_cache, batch_size=batch_size, max_length=448, num_beams=num_beams
)
pipelined_model.generate(input_features, use_cache=use_cache, **kwargs)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[HuggingFaceDocBuilderDev]

The documentation is not available anymore as the PR was closed or merged.

[jimypbr]

Great work!