https://github.com/hops-ops/helm-vllm
Crossplane configuration for vllm Helm chart
https://github.com/hops-ops/helm-vllm
crossplane crossplane-configuration crossplane-configurations crossplane-xrd helm kubernetes vllm xrd
Last synced: 5 months ago
JSON representation
Crossplane configuration for vllm Helm chart
- Host: GitHub
- URL: https://github.com/hops-ops/helm-vllm
- Owner: hops-ops
- Created: 2026-01-14T07:06:22.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2026-01-14T08:16:10.000Z (5 months ago)
- Last Synced: 2026-01-14T12:19:37.723Z (5 months ago)
- Topics: crossplane, crossplane-configuration, crossplane-configurations, crossplane-xrd, helm, kubernetes, vllm, xrd
- Language: Makefile
- Size: 9.77 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# helm-vllm
A Crossplane Configuration package that installs the vLLM production stack Helm chart with a minimal, stable interface.
## Overview
`helm-vllm` renders a single Helm release for vLLM production stack. It exposes only the inputs needed
for chart values, namespace, and release name, keeping the interface stable while allowing full Helm overrides.
## Features
- **Minimal Helm interface**: values and overrideAllValues with stable defaults
- **Predictable naming**: defaults to `-vllm` in the `vllm` namespace
- **GitOps friendly**: ships a `.gitops/` deploy chart
## Prerequisites
- Crossplane installed in the cluster
- Crossplane providers:
- `provider-helm` (>=v1.0.6)
- Crossplane function:
- `function-auto-ready` (>=v0.6.0)
- GPU resources available in the cluster (NVIDIA recommended)
- NVIDIA Kubernetes Device Plugin
## Quick Start
```yaml
apiVersion: pkg.crossplane.io/v1
kind: Configuration
metadata:
name: helm-vllm
spec:
package: ghcr.io/hops-ops/helm-vllm:latest
```
```yaml
apiVersion: helm.hops.ops.com.ai/v1alpha1
kind: VLLM
metadata:
name: vllm
namespace: example-env
spec:
clusterName: example-cluster
values:
servingEngineSpec:
runtimeClassName: nvidia
modelSpec:
- name: llama-3
repository: meta-llama/Llama-3.2-1B-Instruct
gpu: 1
```
## Development
```bash
make render
make validate
make test
```