[SB][CB] mark input tensors refactoring

[yannicks1]

WIP

[github-actions]

👋 Hi! Thank you for contributing to vLLM support on Spyre.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, first install the linting requirements, then run format.sh and commit the changes. This can be done with uv directly:

uv sync --frozen --group lint --active --inexact

Or this can be done with pip:

uv pip compile --group lint > requirements-lint.txt
pip install -r requirements-lint.txt
bash format.sh

Now you are good to go 🚀

[wallashss]

FYI: I did something similar in this other draft PR. My intention is try have common between static batching and continuous batching and in after that have a structure that is more similar to vLLM upstream.

[yannicks1]

thanks for letting me know (I usually do not check draft PRs:)
What do you think about this change? I saw that the order is not the same for SB and CB and just changed it, test seem to pass...

[prashantgupta24]

do we really need this function to be using self? It only interacts with the model_input param

[yannicks1]

you are totally right, I copied it from the static batching code, where it also uses self which can be removed. FYI: @wallashss

[yannicks1]

If @wallashss can confirm above change I will close this PR and he can address all in his?

[wallashss]

If @wallashss can confirm above change I will close this PR and he can address all in his?

I'm back to work in this refactoring, so sure I can address those.

[yannicks1]

Thanks Wallas, closing this one now.