You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
38 lines
1.3 KiB
38 lines
1.3 KiB
deployment:
|
|
image: quay.io/go-skynet/local-ai:latest
|
|
env:
|
|
threads: 14
|
|
contextSize: 512
|
|
modelsPath: "/models"
|
|
volume:
|
|
enabled: false
|
|
|
|
service:
|
|
type: ClusterIP
|
|
annotations: {}
|
|
# If using an AWS load balancer, you'll need to override the default 60s load balancer idle timeout
|
|
# service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: "1200"
|
|
|
|
# Optionally create a PVC containing a model binary, sourced from an arbitrary HTTP server or S3 bucket
|
|
# (requires https://github.com/kubevirt/containerized-data-importer)
|
|
dataVolume:
|
|
enabled: false
|
|
source:
|
|
type: "http" # Source type. One of: [ http | s3 ]
|
|
url: "http://<model_server>/<model_archive>" # e.g. koala-7B-4bit-128g.GGML.tar
|
|
|
|
# CertConfigMap is an optional ConfigMap reference, containing a Certificate Authority (CA) public key
|
|
# and a base64 encoded pem certificate
|
|
caCertConfigMap: ""
|
|
|
|
# SecretExtraHeaders is an optional list of Secret references, each containing an extra HTTP header
|
|
# that may include sensitive information. Only applicable for the http source type.
|
|
secretExtraHeaders: []
|
|
pvc:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
size: 5Gi
|
|
secret:
|
|
enabled: false
|
|
username: "" # base64 encoded
|
|
password: "" # base64 encoded
|
|
|