Repository for dip
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.
 
 
 
 
 
 

60 lines
1.2 KiB

# Default values for kserve.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
# KServe InferenceService 설정
inferenceService:
# InferenceService 이름
name: huggingface-model
# 네임스페이스
namespace: default
# Runtime Class Name
runtimeClassName: nvidia
# 모델 설정
model:
modelFormat:
name: huggingface
args:
- --backend=vllm
- --model_name=phi-1.5
- --dtype=float16
storageUri: "pvc://model-volume/phi-1_5"
image: kserve/huggingfaceserver:v0.15.0-gpu
minReplicas: 0
maxReplicas: 3
# 리소스 설정
resources:
limits:
cpu: "8"
memory: 16Gi
nvidia.com/gpu: "1"
requests:
cpu: "4"
memory: 8Gi
nvidia.com/gpu: "1"
# Ingress 설정
ingress:
enabled: true
namespace: istio-system
className: "kong"
annotations:
cert-manager.io/cluster-issuer: kubeflow-self-signing-issuer
hosts:
- host: "demo01-test1.hopt.paasup.io"
backend:
service:
name: istio-ingressgateway
port: 80
tls:
enabled: true
secretName: kserve-tls
# 이름 오버라이드 설정
nameOverride: ""
fullnameOverride: ""