ychangkim
27 lines
534 B
YAML
27 lines
534 B
YAML
inferenceService:
|
|
name: "{{ .Name }}"
|
|
|
|
model:
|
|
args:
|
|
- --backend=vllm
|
|
- --model_name=$model.name
|
|
- --dtype=float16
|
|
storageUri: "$model.volume"
|
|
|
|
resources:
|
|
limits:
|
|
cpu: "8"
|
|
memory: 16Gi
|
|
nvidia.com/gpu: "1"
|
|
requests:
|
|
cpu: "4"
|
|
memory: 8Gi
|
|
nvidia.com/gpu: "1"
|
|
|
|
ingress:
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: "root-ca-issuer"
|
|
hosts:
|
|
- host: "{{ .Name }}-kserve.{{ .Namespace }}.{{ .Domain }}"
|
|
tls:
|
|
secretName: "{{ .Name }}-tls-secret" |