mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
603d9f5672
* Restrict storage uri to predictor only in transformer collocation Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Add unit tests Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Add e2e test Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * fmt Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Fix e2e test debug info Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Improve quick install script Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Update docs Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * fix indentation on quick install Signed-off-by: Sivanantham Chinnaiyan <[email protected]> --------- Signed-off-by: Sivanantham Chinnaiyan <[email protected]> Signed-off-by: Dan Sun <[email protected]> Co-authored-by: Dan Sun <[email protected]>
46 lines
1.5 KiB
YAML
46 lines
1.5 KiB
YAML
apiVersion: serving.kserve.io/v1beta1
|
|
kind: InferenceService
|
|
metadata:
|
|
name: custom-transformer-collocation
|
|
spec:
|
|
predictor:
|
|
containers:
|
|
- name: kserve-container # Do not change the name; This should be the predictor container
|
|
image: "pytorch/torchserve:0.9.0-cpu"
|
|
args:
|
|
- "torchserve"
|
|
- "--start"
|
|
- "--model-store=/mnt/models/model-store"
|
|
- "--ts-config=/mnt/models/config/config.properties"
|
|
env:
|
|
- name: TS_SERVICE_ENVELOPE
|
|
value: kserve
|
|
- name: STORAGE_URI # This will trigger storage initializer; Should be only present in predictor container
|
|
value: "gs://kfserving-examples/models/torchserve/image_classifier/v1"
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: 1
|
|
memory: 1Gi
|
|
|
|
- name: transformer-container # Do not change the container name
|
|
image: kserve/image-transformer:latest
|
|
args:
|
|
- --model_name=mnist
|
|
- --protocol=v1 # protocol of the predictor; used for converting the input to specific protocol supported by the predictor
|
|
- --http_port=8080
|
|
- --grpc_port=8081
|
|
- --predictor_host=localhost:8085 # predictor listening port
|
|
ports:
|
|
- containerPort: 8080
|
|
protocol: TCP
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: 1
|
|
memory: 1Gi
|