kserve
This commit is contained in:
@@ -23,7 +23,10 @@ inferenceService:
|
||||
- --dtype=float16
|
||||
storageUri: "pvc://model-volume/phi-1_5"
|
||||
image: kserve/huggingfaceserver:v0.15.0-gpu
|
||||
|
||||
|
||||
minReplicas: 0
|
||||
maxReplicas: 3
|
||||
|
||||
# 리소스 설정
|
||||
resources:
|
||||
limits:
|
||||
|
||||
Reference in New Issue
Block a user