Files
kserve/config/runtimes/kserve-huggingfaceserver.yaml

49 lines
1.1 KiB
YAML

apiVersion: serving.kserve.io/v1alpha1
kind: ClusterServingRuntime
metadata:
name: kserve-huggingfaceserver
annotations:
serving.kserve.io/server-type: huggingfaceserver
spec:
annotations:
prometheus.kserve.io/port: '8080'
prometheus.kserve.io/path: "/metrics"
supportedModelFormats:
- name: huggingface
version: "1"
autoSelect: true
priority: 1
protocolVersions:
- v2
- v1
containers:
- name: kserve-container
image: huggingfaceserver:replace
args:
- --model_name={{.Name}}
env:
- name: LMCACHE_USE_EXPERIMENTAL
value: "True"
securityContext:
allowPrivilegeEscalation: false
privileged: false
runAsNonRoot: true
capabilities:
drop:
- ALL
resources:
requests:
cpu: "1"
memory: 2Gi
limits:
cpu: "1"
memory: 2Gi
volumeMounts:
- name: devshm
mountPath: /dev/shm
volumes:
- name: devshm
emptyDir:
medium: Memory
hostIPC: false