Updated docs for autoscaling on gpu. (#328)

Signed-off-by: Andrews Arokiam <[email protected]>
kserve · Mar 24, 2024 · 2ba4317 · 2ba4317
1 parent 144d603
commit 2ba4317
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 2 deletions.
diff --git a/docs/modelserving/autoscaling/autoscale-gpu-new.yaml b/docs/modelserving/autoscaling/autoscale-gpu-new.yaml
@@ -4,6 +4,8 @@ metadata:
   name: "flowers-sample-gpu"
 spec:
   predictor:
+    scaleTarget: 1
+    scaleMetric: concurrency
     model:
       modelFormat:
         name: tensorflow

diff --git a/docs/modelserving/autoscaling/autoscale-new.yaml b/docs/modelserving/autoscaling/autoscale-new.yaml
@@ -2,10 +2,10 @@ apiVersion: "serving.kserve.io/v1beta1"
 kind: "InferenceService"
 metadata:
   name: "flowers-sample"
-  annotations:
-    autoscaling.knative.dev/target: "1"
 spec:
   predictor:
+    scaleTarget: 1
+    scaleMetric: concurrency
     model:
       modelFormat:
         name: tensorflow

diff --git a/docs/modelserving/autoscaling/autoscaling.md b/docs/modelserving/autoscaling/autoscaling.md
@@ -248,6 +248,8 @@ Apply the tensorflow gpu example CR
       name: "flowers-sample-gpu"
     spec:
       predictor:
+        scaleTarget: 1
+        scaleMetric: concurrency
         model:
           modelFormat:
             name: tensorflow
@@ -265,6 +267,8 @@ Apply the tensorflow gpu example CR
     kind: "InferenceService"
     metadata:
       name: "flowers-sample-gpu"
+      annotations:
+        autoscaling.knative.dev/target: "1"
     spec:
       predictor:
         tensorflow: