Fix v1 supported oracle for worker-cls and worker-extension-cls (#15324)

Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

vllm/utils.py

@@ -2170,6 +2170,11 @@ def _maybe_force_spawn():
     if cuda_is_initialized():
         reason = "CUDA is initialized"
     elif is_in_ray_actor():
+        # even if we choose to spawn, we need to pass the ray address
+        # to the subprocess so that it knows how to connect to the ray cluster.
+        # env vars are inherited by subprocesses, even if we use spawn.
+        import ray
+        os.environ["RAY_ADDRESS"] = ray.get_runtime_context().gcs_address
         reason = "In a Ray actor and can only be spawned"
 
     if reason is not None: