Merge pull request #14 from oracle-devrel/cw24

feat: added files from nvidia-nim-oke

Author: WSPluta

nvidia-nim-oke/README.md

@@ -0,0 +1,15 @@
+apiVersion: v2
+name: nim-llm
+description: A Helm chart for NVIDIA NIM for LLMs
+type: application
+kubeVersion: ">=v1.23.0-0"
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.2.1
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.0.0"

nvidia-nim-oke/helm/Chart.yaml

@@ -0,0 +1,27 @@
+image:
+  repository: nvcr.io/nim/meta/llama3-8b-instruct:latest
+  pullPolicy: IfNotPresent
+  model: llama3-8b-instruct
+  numGpus: 1
+
+service:
+  type: ClusterIP
+  openaiPort: 8000
+  annotations: {}
+  labels: {}
+  name: ""  # override the default service name 
+  # below options are deprecated
+  # http_port: 8000  # exposes http interface used in healthchecks to the service
+  # grpc_port: 8001  # exposes the triton grpc interface
+  # metrics_port: 8002  # expose metrics through the main service
+  # openai_port: 8005
+  # nemo_port: 8006
+
+mount:
+  name: /opt/nim/cache
+
+imageCredentials:
+  registry: nvcr.io
+  username: $oauthtoken
+  password: <YOUR_KEY_FROM_NVIDIA>
+  email: <YOUR_EMAIL>

nvidia-nim-oke/helm/values.yaml

@@ -0,0 +1,17 @@
+image:
+  imageName: nvcr.io/nvidia/tritonserver:latest
+  pullPolicy: IfNotPresent
+  model: llama3-8b-instruct
+  numGpus: 1
+
+service:
+  type: LoadBalancer
+
+mount:
+  name: /opt/nim/cache
+
+imageCredentials:
+  registry: nvcr.io
+  username: $oauthtoken
+  password: <YOUR_KEY_FROM_NVIDIA>
+  email: <YOUR_EMAIL>