phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 18:50:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fixing precommit issues

Browse source
This commit is contained in:
Jamie Land 2025-03-18 12:23:30 -04:00
parent 8a61e028da
commit fc627f5c57
5 changed files with 5 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -23,4 +23,4 @@ venv/
pytest-report.xml pytest-report.xml
.coverage .coverage
.python-version .python-version
**/local-* **/local-*

1
chart/README.md
View file

@ -86,7 +86,6 @@ By default llama-stack will use the run.yaml config that comes with the specifie
| `route.tls.enabled` | `bool` | `true` | Enables or disables TLS for the OpenShift Route, providing secure communication. | | `route.tls.enabled` | `bool` | `true` | Enables or disables TLS for the OpenShift Route, providing secure communication. |
| `route.tls.insecureEdgeTerminationPolicy` | `string` | `"Redirect"` | The policy for handling insecure (HTTP) requests when TLS termination is at the edge (Route). | | `route.tls.insecureEdgeTerminationPolicy` | `string` | `"Redirect"` | The policy for handling insecure (HTTP) requests when TLS termination is at the edge (Route). |
| `route.tls.termination` | `string` | `"edge"` | Specifies that TLS termination occurs at the OpenShift Route edge. | | `route.tls.termination` | `string` | `"edge"` | Specifies that TLS termination occurs at the OpenShift Route edge. |
| `runConfig.enabled` | `bool` | `false` | Indicates whether a specific run configuration is enabled. |
| `service.port` | `int` | `5001` | The port on which the Kubernetes Service will be exposed internally within the cluster. | | `service.port` | `int` | `5001` | The port on which the Kubernetes Service will be exposed internally within the cluster. |
| `service.type` | `string` | `"ClusterIP"` | The type of Kubernetes Service. `ClusterIP` makes the service only reachable from within the cluster. | | `service.type` | `string` | `"ClusterIP"` | The type of Kubernetes Service. `ClusterIP` makes the service only reachable from within the cluster. |
| `serviceAccount.annotations` | `object` | `{}` | Annotations for the Kubernetes ServiceAccount. | | `serviceAccount.annotations` | `object` | `{}` | Annotations for the Kubernetes ServiceAccount. |

2
chart/templates/config.yaml
View file

@ -6,4 +6,4 @@ metadata:
data: data:
run.yaml: |- run.yaml: |-
{{- .Files.Get "files/run.yaml" | nindent 4 }} {{- .Files.Get "files/run.yaml" | nindent 4 }}
{{- end }} {{- end }}

2
chart/templates/openshift/route.yaml
View file

@ -28,4 +28,4 @@ spec:
insecureEdgeTerminationPolicy: {{ .Values.route.tls.insecureEdgeTerminationPolicy }} insecureEdgeTerminationPolicy: {{ .Values.route.tls.insecureEdgeTerminationPolicy }}
{{- end }} {{- end }}
wildcardPolicy: None wildcardPolicy: None
{{- end }} {{- end }}

10
chart/values.yaml
View file

@ -17,17 +17,11 @@ vllm:
# https://llama-stack.readthedocs.io/en/latest/distributions/selection.html # https://llama-stack.readthedocs.io/en/latest/distributions/selection.html
distribution: distribution-remote-vllm distribution: distribution-remote-vllm
runConfig:
enabled: false
# customYaml:
# Your custom run.yaml configuration file can be pasted here
# If not set, the default run.yaml file in the `files/run.yaml` will be used
telemetry: telemetry:
enabled: false enabled: false
serviceName: "otel-collector.openshift-opentelemetry-operator.svc.cluster.local:4318" serviceName: "otel-collector.openshift-opentelemetry-operator.svc.cluster.local:4318"
sinks: "console,sqlite,otel" sinks: "console,sqlite,otel"
# Use to allow for other env variables to be passed to the container # Use to allow for other env variables to be passed to the container
# env: # env:
# MY_CUSTOM_ENV_VAR: "my-custom-env-var-value" # MY_CUSTOM_ENV_VAR: "my-custom-env-var-value"
@ -147,7 +141,7 @@ startupProbe:
initialDelaySeconds: 40 initialDelaySeconds: 40
periodSeconds: 10 periodSeconds: 10
failureThreshold: 30 failureThreshold: 30
# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/ # This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
autoscaling: autoscaling:
enabled: false enabled: false