mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Jagadeesh JandGitHub
55a3c4e5c8
* Feat: add huggingface bloom example to torchserve Signed-off-by: Jagadeesh J <[email protected]> * fix: add pv and helper pod yaml - update readme doc - add storageclass yaml - fix config.properties Signed-off-by: Jagadeesh J <[email protected]> * fix: add steps for model sharding
15 lines
338 B
YAML
15 lines
338 B
YAML
apiVersion: serving.kserve.io/v1beta1
|
|
kind: InferenceService
|
|
metadata:
|
|
name: "torchserve-bloom-560m"
|
|
spec:
|
|
predictor:
|
|
pytorch:
|
|
storageUri: pvc://model-cache
|
|
resources:
|
|
limits:
|
|
cpu: 4
|
|
memory: 16Gi
|
|
nvidia.com/gpu: 1
|
|
nodeName: ip-xxx-xxx-xxx-xxx.us-west-2.compute.internal
|