diff --git a/config/manifests/ext_proc.yaml b/config/manifests/ext_proc.yaml
index 49145d24c..f96113e1c 100644
--- a/config/manifests/ext_proc.yaml
+++ b/config/manifests/ext_proc.yaml
@@ -40,7 +40,7 @@ roleRef:
   kind: ClusterRole
   name: pod-read
 ---
-apiVersion: inference.networking.x-k8s.io/v1alpha1
+apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferencePool
 metadata:
   labels:
diff --git a/config/manifests/inferencemodel.yaml b/config/manifests/inferencemodel.yaml
index 2a292c169..57240298a 100644
--- a/config/manifests/inferencemodel.yaml
+++ b/config/manifests/inferencemodel.yaml
@@ -1,4 +1,4 @@
-apiVersion: inference.networking.x-k8s.io/v1alpha1
+apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceModel
 metadata:
   name: inferencemodel-sample
diff --git a/test/testdata/inferencepool-with-model-hermetic.yaml b/test/testdata/inferencepool-with-model-hermetic.yaml
index 372a8512c..c9ca763e1 100644
--- a/test/testdata/inferencepool-with-model-hermetic.yaml
+++ b/test/testdata/inferencepool-with-model-hermetic.yaml
@@ -1,4 +1,4 @@
-apiVersion: inference.networking.x-k8s.io/v1alpha1
+apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferencePool
 metadata:
   name: vllm-llama2-7b-pool
@@ -10,7 +10,7 @@ spec:
   extensionRef:
     name: epp
 ---
-apiVersion: inference.networking.x-k8s.io/v1alpha1
+apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceModel
 metadata:
   name: inferencemodel-sample
@@ -24,7 +24,7 @@ spec:
   - name: sql-lora-1fdg2
     weight: 100
 ---
-apiVersion: inference.networking.x-k8s.io/v1alpha1
+apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceModel
 metadata:
   name: inferencemodel-sheddable
@@ -37,7 +37,7 @@ spec:
   - name: sql-lora-1fdg3
     weight: 100
 ---
-apiVersion: inference.networking.x-k8s.io/v1alpha1
+apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceModel
 metadata:
   name: inferencemodel-generic