Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/source/tutorials/disagg.rst
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ Install the deployment using Helm with the configuration file:

.. code-block:: bash

helm install pd helm/ -f tutorials/assets/values-16-disagg-prefill.yaml
helm install vllm helm/ -f tutorials/assets/values-16-disagg-prefill.yaml
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Using a generic release name like vllm could lead to conflicts if users are running multiple vLLM deployments or following other tutorials in the same Kubernetes cluster. A more specific name would be safer and more descriptive.

Consider using a name that reflects this specific tutorial, for example vllm-disagg-prefill.

    helm install vllm-disagg-prefill helm/ -f tutorials/assets/values-16-disagg-prefill.yaml


This will deploy:

Expand Down Expand Up @@ -172,7 +172,7 @@ First do port forwarding to access the service:

.. code-block:: bash

kubectl port-forward svc/pd-router-service 30080:80
kubectl port-forward svc/vllm-router-service 30080:80
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To maintain consistency with the suggested change to the Helm release name, the service name in this port-forward command should also be updated.

    kubectl port-forward svc/vllm-disagg-prefill-router-service 30080:80


And then send a request to the router by:

Expand Down