gpu: Add embeding service

For a simple RAG pipeline add a embeding service

Signed-off-by: Zvonko Kaiser <zkaiser@nvidia.com>

tests/integration/kubernetes/runtimeclass_workloads/nvidia-nim-llama-3-1-8b-instruct.yaml.in

@@ -1,4 +1,3 @@
-
 # Copyright (c) 2025 NVIDIA Corporation
 #
 # SPDX-License-Identifier: Apache-2.0
@@ -20,7 +19,7 @@ metadata:
     app: ${POD_NAME_INSTRUCT}
 spec:
   restartPolicy: Never
-  runtimeClassName: kata-qemu-nvidia-gpu
+  runtimeClassName: "${RUNTIME_CLASS_NAME}"
   imagePullSecrets:
     - name: ngc-secret-instruct
   securityContext:
@@ -84,6 +83,6 @@ spec:
   volumes:
   - name: nim-cache
     hostPath:
-      path: "/opr/nim/.cache"
+      path: "${LOCAL_NIM_CACHE}"
       type: DirectoryOrCreate
 

tests/integration/kubernetes/runtimeclass_workloads/nvidia-nim-llama-3-2-nv-embedqa-1b-v2.yaml.in

@@ -7,7 +7,6 @@ apiVersion: v1
 kind: Secret
 metadata:
   name: ngc-secret-embedqa
-  namespace: nim-embedqa
 type: kubernetes.io/dockerconfigjson
 data:
   .dockerconfigjson: ${DOCKER_CONFIG_JSON}
@@ -16,7 +15,6 @@ apiVersion: v1
 kind: Pod
 metadata:
   name: nvidia-nim-llama-3-2-nv-embedqa-1b-v2
-  namespace: nim-embedqa
   labels:
     app: nvidia-nim-llama-3-2-nv-embedqa-1b-v2
 spec:
@@ -91,5 +89,5 @@ spec:
   volumes:
   - name: nim-cache
     hostPath:
-      path: "/opr/nim/.cache"
+      path: "${LOCAL_NIM_CACHE}"
       type: DirectoryOrCreate