[ML] Remove scale from 0 feature flag (#116936)

Co-authored-by: Elastic Machine <[email protected]>

Author: davidkyle

test/test-clusters/src/main/java/org/elasticsearch/test/cluster/FeatureFlag.java

@@ -18,8 +18,7 @@
 public enum FeatureFlag {
     TIME_SERIES_MODE("es.index_mode_feature_flag_registered=true", Version.fromString("8.0.0"), null),
     FAILURE_STORE_ENABLED("es.failure_store_feature_flag_enabled=true", Version.fromString("8.12.0"), null),
-    SUB_OBJECTS_AUTO_ENABLED("es.sub_objects_auto_feature_flag_enabled=true", Version.fromString("8.16.0"), null),
-    ML_SCALE_FROM_ZERO("es.ml_scale_from_zero_feature_flag_enabled=true", Version.fromString("8.16.0"), null);
+    SUB_OBJECTS_AUTO_ENABLED("es.sub_objects_auto_feature_flag_enabled=true", Version.fromString("8.16.0"), null);
 
     public final String systemProperty;
     public final Version from;

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/action/TransportInternalInferModelAction.java

@@ -45,7 +45,6 @@
 import org.elasticsearch.xpack.ml.MachineLearning;
 import org.elasticsearch.xpack.ml.inference.InferenceWaitForAllocation;
 import org.elasticsearch.xpack.ml.inference.adaptiveallocations.AdaptiveAllocationsScalerService;
-import org.elasticsearch.xpack.ml.inference.adaptiveallocations.ScaleFromZeroFeatureFlag;
 import org.elasticsearch.xpack.ml.inference.assignment.TrainedModelAssignmentService;
 import org.elasticsearch.xpack.ml.inference.loadingservice.LocalModel;
 import org.elasticsearch.xpack.ml.inference.loadingservice.ModelLoadingService;
@@ -277,13 +276,11 @@ private void inferAgainstAllocatedModel(
             boolean starting = adaptiveAllocationsScalerService.maybeStartAllocation(assignment);
             if (starting) {
                 message += "; starting deployment of one allocation";
-
-                if (ScaleFromZeroFeatureFlag.isEnabled()) {
-                    waitForAllocation.waitForAssignment(
-                        new InferenceWaitForAllocation.WaitingRequest(request, responseBuilder, parentTaskId, listener)
-                    );
-                    return;
-                }
+                logger.debug(message);
+                waitForAllocation.waitForAssignment(
+                    new InferenceWaitForAllocation.WaitingRequest(request, responseBuilder, parentTaskId, listener)
+                );
+                return;
             }
 
             logger.debug(message);