⚗️ add more prompts and cpu validation

[joerunde]

Description

This updates the offline cb example test script to:

• add more varied prompts for better testing with different --max-num-seqs values
• add a --num-prompts option to send more prompts to the model
• add a --compare-with-cpu flag to run the same prompts against the transformers model on cpu and ensure the text is identical

[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 🚀

[yannicks1]

LGTM (did not run it tho)

[yannicks1]

nice:)

[joerunde]

Alright, I'll go ahead and merge and we'll get this over to the compiler team today