Add optional vLLM integration

[lee101]

Summary

• implement vllm_inference helper
• integrate vLLM into server with USE_VLLM toggle
• document vLLM installation and env var
• provide CLI helper and tests for new logic

Testing

• pytest -q tests/unit/test_vllm_env.py tests/unit/test_vllm_inference.py
• ruff check . (fails: Found 297 errors)

---

https://chatgpt.com/codex/tasks/task_e_6847966145208333bcd0c84d4eb29606