Disaggregate prefill decode with zmq

[panf2333]

Add VLLM Connect to start a proxy service and connect to VLLM Server via zmq to improve the performance of prefill and decode phase separation

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀

[mergify]

⚠️ The sha of the head commit of this PR conflicts with #11791. Mergify cannot evaluate rules on this PR. ⚠️