[V1][PP] Enable true PP with Ray executor (#13472)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

vllm/v1/executor/ray_distributed_executor.py

@@ -32,7 +32,7 @@ class RayDistributedExecutor(RayDistributedExecutorV0, Executor):
         """Ray distributed executor supports pipeline parallelism,
         meaning that it allows PP size batches to be executed concurrently.
         """
-        return 1  #self.vllm_config.parallel_config.pipeline_parallel_size
+        return self.parallel_config.pipeline_parallel_size
 
     def execute_model(
         self,