# Kuberay Canary Deployments

**URL:** <https://discuss.ray.io/t/kuberay-canary-deployments/10943>\
**Category:** Ray Clusters\
**Created:** [June 7, 2023, 12:56am UTC](https://discuss.ray.io/t/kuberay-canary-deployments/10943 "2023-06-07T00:56:00Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Brian\_Samsara](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/brian_samsara/32/4553_2.png) [@Brian\_Samsara](https://discuss.ray.io/u/Brian_Samsara)\
**Post date:** [June 7, 2023, 12:56am UTC](https://discuss.ray.io/t/kuberay-canary-deployments/10943/1 "2023-06-07T00:56:00Z")

</div>

[Medium]

For our production Ray serve application, we’d like to perform gradual rollouts to ensure new code is safe. Currently Kuberay performs a complete cutover after confirming the new deployment is good.

An example strategy would be to deploy 10% of traffic for 1 hour and progress to 30%, etc.

Our current solution is to use an external AWS Load Balancer with Target Group to control traffic percentages with Blue/Green cluster setup.

We’ve also explored [Argo Rollouts](https://argo-rollouts.readthedocs.io/en/stable/), however the `RayService` is a CRD and Rollouts is limited to only handling kubernetes `deployments`.

Additions to the Kuberay documentation toward more complex deployment strategies would be appreciated as well.

Testing on Ray 2.4.0 and Kuberay nightly

---

<div class="post-metadata">

**Author:** ![amogkam](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/amogkam/32/17_2.png) [@amogkam](https://discuss.ray.io/u/amogkam)\
**Post date:** [June 7, 2023, 1:01am UTC](https://discuss.ray.io/t/kuberay-canary-deployments/10943/2 "2023-06-07T01:01:43Z")

</div>

cc @Akshay_Malik @Sihan_Wang

---

<div class="post-metadata">

**Author:** ![Akshay\_Malik](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/akshay_malik/32/3807_2.png) [@Akshay\_Malik](https://discuss.ray.io/u/Akshay_Malik)\
**Post date:** [June 7, 2023, 9:57pm UTC](https://discuss.ray.io/t/kuberay-canary-deployments/10943/3 "2023-06-07T21:57:00Z")

</div>

Your solution makes sense. We have some other customers who use ArgoCD successfully, I’m not sure how it differs from Argo Rollouts.

At this point, we don’t have any plans to make changes to the KubeRay deployment strategies.