coreweave-core-workflow-a

name	coreweave-core-workflow-a
description	Deploy KServe InferenceService on CoreWeave with autoscaling and GPU scheduling. Use when serving ML models with KServe, configuring scale-to-zero, or deploying production inference endpoints on CoreWeave. Trigger with phrases like "coreweave inference service", "coreweave kserve", "coreweave model serving", "deploy model on coreweave".
allowed-tools	Read, Write, Edit, Bash(kubectl:*), Grep
version	1.0.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","gpu-cloud","kubernetes","inference","coreweave"]
compatible-with	claude-code

CoreWeave Core Workflow: KServe Inference

Overview

Deploy production inference services on CoreWeave using KServe InferenceService with GPU scheduling, autoscaling, and scale-to-zero. CKS natively integrates with KServe for serverless GPU inference.

Prerequisites

• Completed coreweave-install-auth setup
• KServe available on your CKS cluster
• Model stored in S3, GCS, or HuggingFace

Instructions

Step 1: Deploy an InferenceService

# inference-service.yaml
apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  name: llama-inference
  annotations:
    autoscaling.knative.dev/class: "kpa.autoscaling.knative.dev"
    autoscaling.knative.dev/metric: "concurrency"
    autoscaling.knative.dev/target: "1"
    autoscaling.knative.dev/minScale: "1"
    autoscaling.knative.dev/maxScale: "5"
spec:
  predictor:
    minReplicas: 1
    maxReplicas: 5
    containers:
      - name: kserve-container
        image: vllm/vllm-openai:latest
        args:
          - "--model"
          - "meta-llama/Llama-3.1-8B-Instruct"
          - "--port"
          - "8080"
        
            
             
        
          
             
             
             
          
             
             
             
        
            
            
              
                 
                 
    
      
        
          
             
                  
                   
                   []