[Docs] Add information about using shared memory in docker (#1845)

docs/source/models/adding_model.rst

@@ -18,7 +18,7 @@ This document provides a high-level guide on integrating a `HuggingFace Transfor
 0. Fork the vLLM repository
 --------------------------------
 
-Start by forking our `GitHub <https://github.com/vllm-project/vllm/>`_ repository and then :ref:`build it from source <build_from_source>`.
+Start by forking our `GitHub`_ repository and then :ref:`build it from source <build_from_source>`.
 This gives you the ability to modify the codebase and test your model.
 
 

docs/source/serving/deploying_with_docker.rst

@@ -11,12 +11,20 @@ The image is available on Docker Hub as `vllm/vllm-openai <https://hub.docker.co
 
     $ docker run --runtime nvidia --gpus all \
         -v ~/.cache/huggingface:/root/.cache/huggingface \
-        -p 8000:8000 \
         --env "HUGGING_FACE_HUB_TOKEN=<secret>" \
+        -p 8000:8000 \
+        --ipc=host \
         vllm/vllm-openai:latest \
         --model mistralai/Mistral-7B-v0.1
 
 
+.. note::
+
+        You can either use the ``ipc=host`` flag or ``--shm-size`` flag to allow the
+        container to access the host's shared memory. vLLM uses PyTorch, which uses shared
+        memory to share data between processes under the hood, particularly for tensor parallel inference.
+
+
 You can build and run vLLM from source via the provided dockerfile. To build vLLM:
 
 .. code-block:: console