[cb][test] add tests for volumetric constraint with prefill optimization

[yannicks1]

[cb][test] add tests for volumetric constraint with prefill optimization

Adds tests for the volumetric constraint (PR #363) VLLM_DT_MAX_BATCH_TKV_LIMIT combined with the prefill optimization (PR #340) (currently behind a feature flag VLLM_SPYRE_ENABLE_PREFILL_OPTIMIZATION).

Changes:

• test_requests_use_full_batch_tkv_limit_prefill_opt: just big enough volume -> can prefill sequence with optimization
• test_requests_exceed_batch_tkv_limit_prefill_opt: exceeding volume -> cannot prefill sequence with optimization, have to decode current sequence first...

[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]

bot:test

[joerunde]

lpgtm!