Consolidate samples for deployment of

config/samples/nim/caching/datastore/nimcache.yaml

@@ -0,0 +1,19 @@
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  name: meta-llama3-1b-instruct
+  namespace: nim-service
+spec:
+  source:
+    dataStore:
+      endpoint: http://nemodatastore-sample.nemo.svc.cluster.local:8000/v1/hf
+      modelName: "llama-3-1b-instruct"  # default/llama-3-1b-instruct model must be present in NeMo DataStore
+      authSecret: hf-auth
+      modelPuller: nvcr.io/nvidia/nemo-microservices/nds-v2-huggingface-cli:25.06
+      pullSecret: ngc-secret
+  storage:
+    pvc:
+      create: true
+      storageClass: ""
+      size: "50Gi"
+      volumeAccessMode: ReadWriteOnce

config/samples/nim/caching/hf/nimcache.yaml

@@ -0,0 +1,21 @@
+# NIM Cache with Multi-LLM NIM from HF
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  name: nim-cache-multi-llm
+  namespace: nim-service
+spec:
+  source:
+    hf:
+      endpoint: "https://huggingface.co"
+      namespace: "meta-llama"
+      authSecret: hf-secret # with HF_TOKEN set
+      modelPuller: nvcr.io/nim/nvidia/llm-nim:1.12
+      pullSecret: ngc-secret
+      modelName: "Llama-3.2-1B-Instruct"
+  storage:
+    pvc:
+      create: true
+      storageClass: ''
+      size: "50Gi"
+      volumeAccessMode: ReadWriteOnce

config/samples/nim/caching/ngc-mirror/https/nimcache-llm.yaml

@@ -0,0 +1,24 @@
+# LLM NIM Cache with Mirrored Local Model Registry
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  name: meta-llama3-2-1b-instruct
+  namespace: nim-service
+spec:
+  env:
+    - name: NIM_REPOSITORY_OVERRIDE
+      value: "https://<server-name>:<port>/"
+  source:
+    ngc:
+      modelPuller: nvcr.io/nim/meta/llama-3.2-1b-instruct:1.8
+      pullSecret: ngc-secret
+      authSecret: https-api-secret
+      model:
+        engine: "tensorrt"
+        tensorParallelism: "1"
+  storage:
+    pvc:
+      create: true
+      storageClass: ''
+      size: "50Gi"
+      volumeAccessMode: ReadWriteOnce

config/samples/nim/caching/ngc-mirror/jfrog/nimcache-llm.yaml

@@ -0,0 +1,24 @@
+# LLM NIM Cache with Mirrored Local Model Registry
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  name: meta-llama3-2-1b-instruct
+  namespace: nim-service
+spec:
+  env:
+    - name: NIM_REPOSITORY_OVERRIDE
+      value: "jfrog://<server-name>:<port>/"
+  source:
+    ngc:
+      modelPuller: nvcr.io/nim/meta/llama-3.2-1b-instruct:1.8
+      pullSecret: ngc-secret
+      authSecret: jfrog-api-secret
+      model:
+        engine: "tensorrt"
+        tensorParallelism: "1"
+  storage:
+    pvc:
+      create: true
+      storageClass: ''
+      size: "50Gi"
+      volumeAccessMode: ReadWriteOnce

config/samples/nim/caching/ngc-mirror/s3/nimcache-llm.yaml

@@ -0,0 +1,28 @@
+# LLM NIM Cache with Mirrored Local Model Registry
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  name: meta-llama3-2-1b-instruct
+  namespace: nim-service
+spec:
+  env:
+    - name: NIM_REPOSITORY_OVERRIDE
+      value: "s3://nim_bucket/"
+    - name: AWS_PROFILE
+      value: "default"
+    - name: AWS_REGION
+      value: "us-east-1"
+  source:
+    ngc:
+      modelPuller: nvcr.io/nim/meta/llama-3.2-1b-instruct:1.8
+      pullSecret: ngc-secret
+      authSecret: aws-api-secret
+      model:
+        engine: "tensorrt"
+        tensorParallelism: "1"
+  storage:
+    pvc:
+      create: true
+      storageClass: ''
+      size: "50Gi"
+      volumeAccessMode: ReadWriteOnce

config/samples/nim/caching/ngc/nimcache.yaml

@@ -0,0 +1,22 @@
+# NIM Cache with LLM-Specific NIM from NGC
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  labels:
+    app.kubernetes.io/name: k8s-nim-operator
+  name: meta-llama-3-2-1b-instruct
+  namespace: nim-service
+spec:
+  source:
+    ngc:
+      modelPuller: nvcr.io/nim/meta/llama-3.2-1b-instruct:1.8
+      pullSecret: ngc-secret
+      authSecret: ngc-api-secret
+      model:
+        engine: "tensorrt"
+        tensorParallelism: "1"
+  storage:
+    pvc:
+      create: true
+      size: "50Gi"
+      volumeAccessMode: ReadWriteOnce