🥅 disable v0 decoders

[joerunde]

Description

This updates our platform.py to disable v0 for generation, since it will be no longer supported in fms 1.1.0

Related to #241

Unfortunately the entire v0 stack needs to remain in place for embeddings models, which require the v0 scheduler, v0 worker, and v0 embeddings model runner (which is a child of the v0 decoder model runner)

[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]

lgtm