diff --git a/inference/core/version.py b/inference/core/version.py
index 805233dd02..21cbaccbb2 100644
--- a/inference/core/version.py
+++ b/inference/core/version.py
@@ -1,4 +1,4 @@
-__version__ = "0.9.14rc2"
+__version__ = "0.9.14"
 
 
 if __name__ == "__main__":
diff --git a/inference/enterprise/workflows/complier/steps_executors/models.py b/inference/enterprise/workflows/complier/steps_executors/models.py
index a2531048a2..a3d9d65ff0 100644
--- a/inference/enterprise/workflows/complier/steps_executors/models.py
+++ b/inference/enterprise/workflows/complier/steps_executors/models.py
@@ -1096,7 +1096,7 @@ async def get_cogvlm_generations_locally(
             core_model="cogvlm",
             api_key=api_key,
         )
-        result = await model_manager.model_manager(
+        result = await model_manager.infer_from_request(
             yolo_world_model_id, inference_request
         )
         serialised_result.append(
diff --git a/tests/inference/unit_tests/enterprise/workflows/compiler/steps_executors/test_models.py b/tests/inference/unit_tests/enterprise/workflows/compiler/steps_executors/test_models.py
index aeff002176..083072f225 100644
--- a/tests/inference/unit_tests/enterprise/workflows/compiler/steps_executors/test_models.py
+++ b/tests/inference/unit_tests/enterprise/workflows/compiler/steps_executors/test_models.py
@@ -536,7 +536,7 @@ async def test_get_cogvlm_generations_from_remote_api(
 async def test_get_cogvlm_generations_locally() -> None:
     # given
     model_manager = AsyncMock()
-    model_manager.model_manager.side_effect = [
+    model_manager.infer_from_request.side_effect = [
         CogVLMResponse.parse_obj({"response": "Response 1: 42"}),
         CogVLMResponse.parse_obj({"response": "Response 2: 42"}),
         CogVLMResponse.parse_obj({"response": "Response 3: 42"}),
@@ -569,7 +569,7 @@ async def test_run_cog_vlm_prompting_when_local_execution_chosen_and_no_expected
 ):
     # given
     model_manager = AsyncMock()
-    model_manager.model_manager.side_effect = [
+    model_manager.infer_from_request.side_effect = [
         CogVLMResponse.parse_obj({"response": "Response 1: 42"}),
         CogVLMResponse.parse_obj({"response": "Response 2: 42"}),
         CogVLMResponse.parse_obj({"response": "Response 3: 42"}),
@@ -606,7 +606,7 @@ async def test_run_cog_vlm_prompting_when_local_execution_chosen_and_json_output
 ):
     # given
     model_manager = AsyncMock()
-    model_manager.model_manager.side_effect = [
+    model_manager.infer_from_request.side_effect = [
         CogVLMResponse.parse_obj({"response": json.dumps({"value": 42})}),
         CogVLMResponse.parse_obj({"response": json.dumps({"value": 43})}),
         CogVLMResponse.parse_obj({"response": json.dumps({"value": 44})}),