[v0] replace current_platform with SpyrePlatform

[yannicks1]

[v0] replace current_platform with SpyrePlatform

PR #47 missed replacing current_platform with SpyrePlatform in the v0 model runner. I don't think this is an issue or related to the recent failures of v0 static batching on AIU Spyre, just add it here for completeness.

[yannicks1]

@joerunde could we easily use the comment bot to launch v0 SB tests on AIU Spyre with the latest image (where it was failing previously) or have v0 decoder models been completely removed from the testing pipeline?

[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 🚀

[joerunde]

@yannicks1 yeah you can use the bot here. Decoder support has been completely removed from V0, but the model runner is still used for embeddings

[joerunde]

bot:test
MARKERS=embedding

[joerunde]

bot:test
MARKERS=embedding

[joerunde]

Tests LGTM!