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.
29 lines
582 B
29 lines
582 B
# KServe Custom Values
|
|
inferenceService:
|
|
name: "phi-1_5"
|
|
|
|
model:
|
|
args:
|
|
- --backend=vllm
|
|
- --model_name=phi-1_5
|
|
- --dtype=float16
|
|
storageUri: "pvc://model-volume/phi-1_5"
|
|
image: kserve/huggingfaceserver:v0.15.0-gpu
|
|
|
|
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: "phi15.default.hopt.paasup.io"
|
|
tls:
|
|
secretName: custom-kserve-tls
|
|
|