Application Auto Scaling Update: Application Auto Scaling is now more responsive to the changes in demand of your SageMaker Inference endpoints. To get started, create or update a Target Tracking policy based on High Resolution CloudWatch metrics.

AWS · AWS · commit 6f78fc5efd77 · 2024-07-25T19:30:30.000Z
diff --git a/.changes/next-release/feature-ApplicationAutoScaling-ad5f039.json b/.changes/next-release/feature-ApplicationAutoScaling-ad5f039.json
@@ -0,0 +1,6 @@
+{
+    "type": "feature",
+    "category": "Application Auto Scaling",
+    "contributor": "",
+    "description": "Application Auto Scaling is now more responsive to the changes in demand of your SageMaker Inference endpoints. To get started, create or update a Target Tracking policy based on High Resolution CloudWatch metrics."
+}
diff --git a/services/applicationautoscaling/src/main/resources/codegen-resources/service-2.json b/services/applicationautoscaling/src/main/resources/codegen-resources/service-2.json
@@ -697,7 +697,9 @@
         "SageMakerVariantProvisionedConcurrencyUtilization",
         "ElastiCacheDatabaseCapacityUsageCountedForEvictPercentage",
         "SageMakerInferenceComponentInvocationsPerCopy",
-        "WorkSpacesAverageUserSessionsCapacityUtilization"
+        "WorkSpacesAverageUserSessionsCapacityUtilization",
+        "SageMakerInferenceComponentConcurrentRequestsPerCopyHighResolution",
+        "SageMakerVariantConcurrentRequestsPerModelHighResolution"
       ]
     },
     "MetricUnit":{"type":"string"},
