🎨 Remove new_token_ids from warmup

[prashantgupta24]

Description

🎨 Remove new_token_ids from warmup since new_token_ids are not used anymore.

[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 🚀

[prashantgupta24]

bot:test
MARKERS="cb and spyre"

[joerunde]

does this need to be set to anything? I'm actually not clear on whether or not the prefill pass returns a first sampled token which may be cached here

[prashantgupta24]

The prefill pass does return a sampled token, but that caching happens within the execute_model and hence we don't need to pass in new_token_ids anymore.

[joerunde]

@prashantgupta24 do we wanna get this merged?

If so we should definitely test to triple-check that this works with the upcoming compiler changes for continuous batching

[prashantgupta24]

No hurry as such, don't want to add anything before the release lol