mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Dan SunandGitHub
9fb3057831
* Update bert tokenizer example Signed-off-by: Dan Sun <[email protected]> * Generate id for infer request Signed-off-by: Dan Sun <[email protected]> * Fix model name in tests Signed-off-by: Dan Sun <[email protected]> * Fix model_name argument Signed-off-by: Dan Sun <[email protected]> * Fix predictor_protocol Signed-off-by: Dan Sun <[email protected]> * Generate request id if none Signed-off-by: Dan Sun <[email protected]> * Set default None for PredictorConfig Signed-off-by: Dan Sun <[email protected]> * Add comment Signed-off-by: Dan Sun <[email protected]> * Enable doc with default values Signed-off-by: Dan Sun <[email protected]> * Add back add_help false Signed-off-by: Dan Sun <[email protected]> * Update protocol choices Signed-off-by: Dan Sun <[email protected]> * Fix grpc-v2 choice Signed-off-by: Dan Sun <[email protected]> --------- Signed-off-by: Dan Sun <[email protected]>
24 lines
577 B
YAML
24 lines
577 B
YAML
apiVersion: "serving.kserve.io/v1beta1"
|
|
kind: "InferenceService"
|
|
metadata:
|
|
name: "bert-v2"
|
|
spec:
|
|
transformer:
|
|
containers:
|
|
- name: kserve-container
|
|
image: kserve/bert-tokenizer:latest
|
|
env:
|
|
- name: STORAGE_URI
|
|
value: "gs://kfserving-examples/models/triton/bert-transformer"
|
|
predictor:
|
|
triton:
|
|
runtimeVersion: 23.10-py3
|
|
resources:
|
|
limits:
|
|
cpu: "1"
|
|
memory: 8Gi
|
|
requests:
|
|
cpu: "1"
|
|
memory: 8Gi
|
|
storageUri: "gs://kfserving-examples/models/triton/bert"
|