[CB][do not merge] Support batch size 1 for decode, simplify warmup

[yannicks1]

[CB][do not merge] Support batch size 1 for decode, simplify warmup

As we now switched to torch 2.7.1 in #307 , dynamic dimension of size 1 are supported by torch. Hence, batch size 1 for decode should produce the same graph as batch size >= 2. This PR relaxes the constraint and adapts the warmup. To be tested on the card. if working, this makes #287 redundant.

[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
TEST_FILE=tests/e2e/test_spyre_cb.py MARKERS="spyre"

[yannicks1]

bot test failed in warmup decode.

[yannicks1]

bot:test
TEST_FILE=tests/e2e/test_spyre_cb.py MARKERS="spyre"

[yannicks1]

Note: CPU failures is expected for BS 1 (didnt adapt warmup as in #287 )

Spyre card: reverting the warmup changes results in a runtime error: compile graph failed

[yannicks1]

Looks like batch size 1 for decode is not supported by the compiler yet... Priority of this is low as performance advantage is marginal paired with a limited use case.

[yannicks1]

update: i tried Joshs suggestion, so far without success