Files
2023-01-10 04:31:39 -08:00

13 lines
292 B
YAML

apiVersion: "serving.kserve.io/v1beta1"
kind: "InferenceService"
metadata:
name: "pytorch-batcher"
spec:
predictor:
minReplicas: 1
batcher:
maxBatchSize: 16
maxLatency: 300
pytorch:
storageUri: "gs://kfserving-examples/models/torchserve/image_classifier/v1"