Integrate with KServe (#3202)
* Integrate with KServe, To #48853387 Signed-off-by: cheyang <cheyang@163.com> * Remove update from operations in kserve, To #48853387 Signed-off-by: cheyang <cheyang@163.com> --------- Signed-off-by: cheyang <cheyang@163.com>
This commit is contained in:
GitHub
parent
d103d62f8f
commit
886a5c114c
|
|
@ -0,0 +1,311 @@
|
|||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-lgbserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- args:
|
||||
- --model_name={{.Name}}
|
||||
- --model_dir=/mnt/models
|
||||
- --http_port=8080
|
||||
- --nthread=1
|
||||
image: kserve/lgbserver:v0.10.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: lightgbm
|
||||
version: "3"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-mlserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- env:
|
||||
- name: MLSERVER_MODEL_IMPLEMENTATION
|
||||
value: '{{.Labels.modelClass}}'
|
||||
- name: MLSERVER_HTTP_PORT
|
||||
value: "8080"
|
||||
- name: MLSERVER_GRPC_PORT
|
||||
value: "9000"
|
||||
- name: MODELS_DIR
|
||||
value: /mnt/models
|
||||
image: docker.io/seldonio/mlserver:1.0.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v2
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: sklearn
|
||||
version: "0"
|
||||
- autoSelect: true
|
||||
name: xgboost
|
||||
version: "1"
|
||||
- autoSelect: true
|
||||
name: lightgbm
|
||||
version: "3"
|
||||
- autoSelect: true
|
||||
name: mlflow
|
||||
version: "1"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-paddleserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- args:
|
||||
- --model_name={{.Name}}
|
||||
- --model_dir=/mnt/models
|
||||
- --http_port=8080
|
||||
image: kserve/paddleserver:v0.10.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: paddle
|
||||
version: "2"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-pmmlserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- args:
|
||||
- --model_name={{.Name}}
|
||||
- --model_dir=/mnt/models
|
||||
- --http_port=8080
|
||||
image: kserve/pmmlserver:v0.10.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: pmml
|
||||
version: "3"
|
||||
- autoSelect: true
|
||||
name: pmml
|
||||
version: "4"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-sklearnserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- args:
|
||||
- --model_name={{.Name}}
|
||||
- --model_dir=/mnt/models
|
||||
- --http_port=8080
|
||||
image: kserve/sklearnserver:v0.10.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: sklearn
|
||||
version: "1"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-tensorflow-serving
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- args:
|
||||
- --model_name={{.Name}}
|
||||
- --port=9000
|
||||
- --rest_api_port=8080
|
||||
- --model_base_path=/mnt/models
|
||||
- --rest_api_timeout_in_ms=60000
|
||||
command:
|
||||
- /usr/bin/tensorflow_model_server
|
||||
image: tensorflow/serving:2.6.2
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
- grpc-v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: tensorflow
|
||||
version: "1"
|
||||
- autoSelect: true
|
||||
name: tensorflow
|
||||
version: "2"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-torchserve
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8082"
|
||||
containers:
|
||||
- args:
|
||||
- torchserve
|
||||
- --start
|
||||
- --model-store=/mnt/models/model-store
|
||||
- --ts-config=/mnt/models/config/config.properties
|
||||
env:
|
||||
- name: TS_SERVICE_ENVELOPE
|
||||
value: '{{.Labels.serviceEnvelope}}'
|
||||
image: pytorch/torchserve-kfs:0.7.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
- v2
|
||||
- grpc-v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: pytorch
|
||||
version: "1"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-tritonserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8002"
|
||||
containers:
|
||||
- args:
|
||||
- tritonserver
|
||||
- --model-store=/mnt/models
|
||||
- --grpc-port=9000
|
||||
- --http-port=8080
|
||||
- --allow-grpc=true
|
||||
- --allow-http=true
|
||||
image: nvcr.io/nvidia/tritonserver:21.09-py3
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v2
|
||||
- grpc-v2
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: tensorrt
|
||||
version: "8"
|
||||
- autoSelect: true
|
||||
name: tensorflow
|
||||
version: "1"
|
||||
- autoSelect: true
|
||||
name: tensorflow
|
||||
version: "2"
|
||||
- autoSelect: true
|
||||
name: onnx
|
||||
version: "1"
|
||||
- name: pytorch
|
||||
version: "1"
|
||||
- autoSelect: true
|
||||
name: triton
|
||||
version: "2"
|
||||
---
|
||||
apiVersion: serving.kserve.io/v1alpha1
|
||||
kind: ClusterServingRuntime
|
||||
metadata:
|
||||
name: kserve-xgbserver
|
||||
spec:
|
||||
annotations:
|
||||
prometheus.kserve.io/path: /metrics
|
||||
prometheus.kserve.io/port: "8080"
|
||||
containers:
|
||||
- args:
|
||||
- --model_name={{.Name}}
|
||||
- --model_dir=/mnt/models
|
||||
- --http_port=8080
|
||||
- --nthread=1
|
||||
image: kserve/xgbserver:v0.10.0
|
||||
name: kserve-container
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: "1"
|
||||
memory: 2Gi
|
||||
protocolVersions:
|
||||
- v1
|
||||
supportedModelFormats:
|
||||
- autoSelect: true
|
||||
name: xgboost
|
||||
version: "1"
|
||||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue