test tensorflow

clusters/k3s-dgx/apps/huihui-granite-inference.yaml

@@ -1,22 +1,18 @@
 apiVersion: "serving.kserve.io/v1beta1"
 kind: "InferenceService"
 metadata:
-  name: "qwen-llm"
+  name: "flower-sample"
   namespace: kserve
 spec:
   predictor:
     model:
       modelFormat:
-        name: huggingface
-      args:
-        - --model_name=qwen
-      storageUri: "hf://Qwen/Qwen2.5-0.5B-Instruct"
+        name: tensorflow
+      storageUri: "gs://kfserving-examples/models/tensorflow/flowers"
       resources:
-        limits:
-          cpu: "2"
-          memory: 6Gi
-          nvidia.com/gpu: "1"
         requests:
+          cpu: "100m"
+          memory: "256Mi"
+        limits:
           cpu: "1"
-          memory: 4Gi
-          nvidia.com/gpu: "1"
+          memory: "1Gi"