fixed and removed 1 new instance of runtime ClassName

Author: tbazant

references/vllm-helm-overrides.adoc

@@ -111,7 +111,6 @@ The following {vllm} override file includes basic configuration options.
 * Access to a {huggingface} token (`HF_TOKEN`).
 * The model `meta-llama/Llama-3.1-8B-Instruct` from this example is a gated model that requires you to accept the agreement to access it.
 For more information, see link:https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct[].
-* The `runtimeClassName` specified here is `nvidia`.
 * Update the `storageClass:` entry for each `modelSpec`.
 
 [source,yaml]
@@ -121,7 +120,7 @@ global:
   imagePullSecrets:
   - application-collection
 servingEngineSpec:
-    modelSpec:
+  modelSpec:
   - name: "llama3" <.>
     registry: "dp.apps.rancher.io" <.>
     repository: "containers/vllm-openai" <.>
@@ -262,7 +261,7 @@ global:
   imagePullSecrets:
   - application-collection
 servingEngineSpec:
-    modelSpec:
+  modelSpec:
   - name: "llama3"
     registry: "dp.apps.rancher.io"
     repository: "containers/vllm-openai"
@@ -381,7 +380,7 @@ global:
   imagePullSecrets:
   - application-collection
 servingEngineSpec:
-    modelSpec:
+  modelSpec:
   - name: "mistral"
     registry: "dp.apps.rancher.io"
     repository: "containers/lmcache-vllm-openai"
@@ -429,7 +428,7 @@ global:
   imagePullSecrets:
   - application-collection
 servingEngineSpec:
-    modelSpec:
+  modelSpec:
   - name: "mistral"
     registry: "dp.apps.rancher.io"
     repository: "containers/lmcache-vllm-openai"

tasks/NVIDIA-Operator-installation.adoc

@@ -164,7 +164,7 @@ metadata:
   namespace: default
 spec:
   restartPolicy: OnFailure
-    containers:
+  containers:
   - name: cuda-container
     image: nvcr.io/nvidia/k8s/cuda-sample:nbody
     args: ["nbody", "-gpu", "-benchmark"]