[serve][llm] Deliver raw HTTP requests to LLM engine

[eicherseiji]

Why are these changes needed?

• Serve deployment handle routers benefit from arbitrary headers on the raw HTTP request
• vLLM engine expects access to the raw HTTP headers for request ID

Propagation:

FastAPI Endpoint (router.py)
    ↓ request: Request
LLMRouter methods (chat, completions, embeddings, score)
    ↓ raw_request
_process_llm_request / _get_response
    ↓ raw_request
DeploymentHandle.remote(body, raw_request)
    ↓ raw_request
LLMServer methods
    ↓ raw_request
_run_request
    ↓ raw_request
LLMEngine methods (vLLMEngine)
    ↓ raw_request
vLLM OpenAI serving methods

Related issue number

Checks

• I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
• I've run pre-commit jobs to lint the changes in this PR. (pre-commit setup)
• I've included any doc changes needed for https://docs.ray.io/en/master/.
  • I've added any new APIs to the API Reference. For example, if I added a
    method in Tune, I've added it in doc/source/tune/api/ under the
    corresponding .rst file.
• I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
• Testing Strategy
  • Unit tests
  • Release tests
  • This PR is not tested :(

[eicherseiji]

@kouroshHakha do you want to leave these here?

[github-actions]

This pull request has been automatically marked as stale because it has not had
any activity for 14 days. It will be closed in another 14 days if no further activity occurs.
Thank you for your contributions.

You can always ask for help on our discussion forum or Ray's public slack channel.

If you'd like to keep this open, just leave any comment, and the stale label will be removed.