Updates artifacts for v0.1.0-rc1 release (#285)

Signed-off-by: Daneyon Hansen <[email protected]>

Author: danehans

pkg/README.md

@@ -23,7 +23,7 @@ This quickstart guide is intended for engineers familiar with k8s and model serv
 1. **Install the Inference Extension CRDs:**
 
    ```sh
-   kubectl apply -k https://github.com/kubernetes-sigs/gateway-api-inference-extension/config/crd
+   kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v0.1.0-rc1/manifests.yaml
    ```
 
 1. **Deploy InferenceModel**

pkg/manifests/ext_proc.yaml

@@ -71,7 +71,8 @@ spec:
     spec:
       containers:
       - name: inference-gateway-ext-proc
-        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:main
+        image: us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/epp:v0.1.0-rc1
+        imagePullPolicy: IfNotPresent
         args:
         - -poolName
         - "vllm-llama2-7b-pool"

pkg/manifests/vllm/deployment.yaml

@@ -14,8 +14,8 @@ spec:
     spec:
       containers:
         - name: lora
-          image: "vllm/vllm-openai:latest"
-          imagePullPolicy: Always
+          image: "vllm/vllm-openai:v0.7.1"
+          imagePullPolicy: IfNotPresent
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:
           - "--model"