mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
* update fluid kserve demo to use huggingface servingruntime and other model. Signed-off-by: Lize Cai <[email protected]> * fix lint Signed-off-by: Lize Cai <[email protected]> * explicitly set custom servingruntime, update devshm. Signed-off-by: Lize Cai <[email protected]> * update the args in custom kserve hfserver Signed-off-by: Lize Cai <[email protected]> * address comments Signed-off-by: Lize Cai <[email protected]> * add return of line Signed-off-by: Lize Cai <[email protected]> --------- Signed-off-by: Lize Cai <[email protected]>
13 lines
247 B
YAML
13 lines
247 B
YAML
apiVersion: data.fluid.io/v1alpha1
|
|
kind: DataLoad
|
|
metadata:
|
|
name: s3-dataload
|
|
spec:
|
|
dataset:
|
|
name: s3-data
|
|
namespace: kserve-fluid-demo
|
|
target:
|
|
# # please update it accordingly
|
|
- path: /llama-31-8b-instruct
|
|
replicas: 3
|