[Misc] Deprecation Warning when setting --engine-use-ray (#7424)

Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: youkaichao <youkaichao@126.com>

vllm/envs.py

@@ -55,6 +55,7 @@ if TYPE_CHECKING:
     VERBOSE: bool = False
     VLLM_ALLOW_LONG_MAX_MODEL_LEN: bool = False
     VLLM_TEST_FORCE_FP8_MARLIN: bool = False
+    VLLM_ALLOW_ENGINE_USE_RAY: bool = False
     VLLM_PLUGINS: Optional[List[str]] = None
 
 
@@ -364,6 +365,14 @@ environment_variables: Dict[str, Callable[[], Any]] = {
     (os.environ.get("VLLM_TEST_FORCE_FP8_MARLIN", "0").strip().lower() in
      ("1", "true")),
 
+    # If set, allow running the engine as a separate ray actor,
+    # which is a deprecated feature soon to be removed.
+    # See https://github.com/vllm-project/vllm/issues/7045
+    "VLLM_ALLOW_ENGINE_USE_RAY":
+    lambda:
+    (os.environ.get("VLLM_ALLOW_ENGINE_USE_RAY", "0").strip().lower() in
+     ("1", "true")),
+
     # a list of plugin names to load, separated by commas.
     # if this is not set, it means all plugins will be loaded
     # if this is set to an empty string, no plugins will be loaded