mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
62 lines
1.5 KiB
YAML
62 lines
1.5 KiB
YAML
apiVersion: serving.kserve.io/v1alpha1
|
|
kind: ClusterServingRuntime
|
|
metadata:
|
|
name: kserve-tritonserver
|
|
annotations:
|
|
serving.kserve.io/server-type: tritonserver
|
|
spec:
|
|
annotations:
|
|
prometheus.kserve.io/port: '8002'
|
|
prometheus.kserve.io/path: "/metrics"
|
|
supportedModelFormats:
|
|
- name: tensorrt
|
|
version: "8"
|
|
autoSelect: true
|
|
priority: 1
|
|
- name: tensorflow
|
|
version: "1"
|
|
autoSelect: true
|
|
priority: 1
|
|
- name: tensorflow
|
|
version: "2"
|
|
autoSelect: true
|
|
priority: 1
|
|
- name: onnx
|
|
version: "1"
|
|
autoSelect: true
|
|
priority: 1
|
|
- name: pytorch
|
|
version: "1"
|
|
- name: triton
|
|
version: "2"
|
|
autoSelect: true
|
|
priority: 1
|
|
protocolVersions:
|
|
- v2
|
|
- grpc-v2
|
|
containers:
|
|
- name: kserve-container
|
|
image: kserve-tritonserver:replace
|
|
args:
|
|
- tritonserver
|
|
- --model-store=/mnt/models
|
|
- --grpc-port=9000
|
|
- --http-port=8080
|
|
- --allow-grpc=true
|
|
- --allow-http=true
|
|
securityContext:
|
|
runAsUser: 1000 # https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/customization_guide/deploy.html#run-as-a-non-root-user
|
|
allowPrivilegeEscalation: false
|
|
privileged: false
|
|
runAsNonRoot: true
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
resources:
|
|
requests:
|
|
cpu: "1"
|
|
memory: 2Gi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 2Gi
|