[Bugfix] Fix multi nodes TP+PP for XPU (#8884)

Signed-off-by: YiSheng5 <syhm@mail.ustc.edu.cn>
Signed-off-by: yan ma <yan.ma@intel.com>
Co-authored-by: YiSheng5 <syhm@mail.ustc.edu.cn>

docs/source/getting_started/xpu-installation.rst

@@ -60,3 +60,21 @@ Build from source
     - FP16 is the default data type in the current XPU backend. The BF16 data
       type will be supported in the future.
 
+
+Distributed inference and serving
+---------------------------------
+
+XPU platform supports tensor-parallel inference/serving and also supports pipeline parallel as a beta feature for online serving. We requires Ray as the distributed runtime backend. For example, a reference execution likes following:
+
+.. code-block:: console
+
+    $ python -m vllm.entrypoints.openai.api_server \
+    $      --model=facebook/opt-13b \
+    $      --dtype=bfloat16 \
+    $      --device=xpu \
+    $      --max_model_len=1024 \
+    $      --distributed-executor-backend=ray \
+    $      --pipeline-parallel-size=2 \
+    $      -tp=8
+
+By default, a ray instance will be launched automatically if no existing one is detected in system, with ``num-gpus`` equals to ``parallel_config.world_size``. We recommend properly starting a ray cluster before execution, referring helper `script <https://github.com/vllm-project/vllm/tree/main/examples/run_cluster.sh>`_.