Skip to main content

Deploy vLLM for Inference

Deploy and scale vLLM inference workloads on CoreWeave Kubernetes Service (CKS)

Outline​

This long-form tutorial is comprised of the pages underneath this section. They are designed to be followed in the order they are numbered.

In this tutorial, you will:

  1. Set up infrastructure dependencies.
  2. Configure monitoring and observability.
  3. Deploy vLLM inference service.
  4. Monitor performance and test autoscaling.
🚀 What you'll need

Before you start, you must have:

  • A working CKS cluster with GPU and CPU nodes.
  • The following tools installed on your local machine:
    • Kubectl which needs to be connected to your cluster.
    • Helm version 3.8+
    • Git
  • Access to Hugging Face models (with tokens if required for gated models).
🔧 What you'll use

In this tutorial, you'll use the following tools and services:

  • vLLM: High-performance LLM inference engine
  • Traefik: Ingress controller for external traffic routing
  • cert-manager: Automatic TLS certificate management
  • Prometheus & Grafana: Monitoring and observability stack
  • KEDA: Kubernetes Event-driven Autoscaling
  • CoreWeave Helm charts: Pre-configured deployment templates

Architecture overview​

The complete vLLM inference solution consists of several components working together:

  • vLLM service: The main inference engine running your language model
  • Traefik ingress: Handles external traffic routing and TLS termination
  • cert-manager: Manages automatic SSL certificate generation and renewal
  • Prometheus: Collects metrics from vLLM and other components
  • Grafana: Provides dashboards for monitoring inference performance
  • KEDA: Enables autoscaling based on custom metrics like request queue depth

Prerequisites​

Verify the following:

  • You can access your cluster using kubectl.

    For example, run the following command:

    Example
    $
    kubectl cluster-info

    You should see something similar to the following:

    Kubernetes control plane is running at...

    CoreDNS is running at...

    node-local-dns is running at...

  • Your cluster has at least one CPU node.

    For example, run the following command:

    Example
    $
    kubectl get nodes -o=custom-columns="NAME:metadata.name,CLASS:metadata.labels['node\.coreweave\.cloud\/class']"

    You should see something similar to the following:

    NAME      CLASS

    g137a10   gpu

    g5424e0   cpu

    g77575e   cpu

    gd926d4   gpu

  • Ensure your CKS cluster has GPU Nodes with at least 16GB of GPU memory, required by the Llama 3.1 8B Instruct model used in this tutorial.

    For example, run the following command:

    Example
    $
    kubectl get nodes -o=custom-columns="NAME:metadata.name,IP:status.addresses[?(@.type=='InternalIP')].address,TYPE:metadata.labels['node\.coreweave\.cloud\/type'],RESERVED:metadata.labels['node\.coreweave\.cloud\/reserved'],NODEPOOL:metadata.labels['compute\.coreweave\.com\/node-pool'],READY:status.conditions[?(@.type=='Ready')].status,GPU:metadata.labels['gpu\.nvidia\.com/model'],VRAM:metadata.labels['gpu\.nvidia\.com/vram']"

    You should see something similar to the following:

    NAME      IP               TYPE         RESERVED   NODEPOOL    READY   GPU           VRAM

    g80eac0   10.176.212.195   gd-1xgh200   cw9a2f     infer-gpu   True    GH200_480GB   97

    gf2809a   10.176.244.33    turin-gp-l   cw9a2f     infer-cpu   True

    Under VRAM, the number should be 16 or greater.

    Tip

    To further debug and diagnose cluster problems, use kubectl cluster-info dump.

Additional resources and information​

The following tools are preinstalled on CKS worker nodes:

  • Docker: Container runtime for running vLLM inference pods
  • NVIDIA drivers: GPU drivers for CUDA acceleration
  • CoreWeave CSI drivers: Storage drivers for persistent volumes
  • CoreWeave CNI: Network plugins for pod communication

To learn more about vLLM, and inference on CoreWeave, check out the following resources:

Next ➡ Set up infrastructure dependencies

Last updated on