vllm-project / vllm-project/production-stack
feature: Helm chart improvements
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Python
- Stars
- 2.6k
- Forks
- 503
- Avg merge
- 4d 17h
- Merged PRs (30d)
- 8
Description
Describe the feature
Hi,
While deploying the helm chart, I faced a few issues:
- PodDisruptionBudget does not work
- I can't deploy the serviceMonitor without the whole kube-prometheus-stack, prometheus operator is already deployed on my cluster
- there is no way to add extraManifest likean externalSecret
- I shouldn't need a bash sript to deploy the serviceMonitor and the grafana dashboard
Why do you need this feature?
I think improving the helm chart would be nice so it can be "prod ready".
If the plan sounds good, I can submit a few PRs to
- address the PDB
- add a template for service Monitor directly in the vllm chart
- add a template for grafana dashboards
- add kube-prometheus-stack as a sub-chart
- add an extraManifest value
Additional context
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the repository's Helm chart templates and values, focusing on the PodDisruptionBudget, ServiceMonitor, Grafana dashboard, sub-chart, and extraManifest areas described in the issue. Done means the chart supports these deployment options without external Bash scripts and works with an already deployed Prometheus Operator.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- grafana, helm, kubernetes, prometheus
- Domain
- devops, infrastructure, observability
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100