[V0 Deprecation] Remove V0 Spec Decode workers

[WoosukKwon]

This PR removes the spec decoding code in vLLM V0, which is almost superseded by vLLM V1.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Code Review

This pull request is a large-scale cleanup that removes the V0 implementation for speculative decoding. The changes consist almost entirely of deleting the V0 spec decode workers and their associated tests. The only logical modification is in vllm/platforms/cuda.py, which now correctly raises a NotImplementedError if an attempt is made to use speculative decoding with the V0 engine. This is a clean and effective way to remove a deprecated feature. The changes appear correct and align with the PR's objective.