diff --git a/pyproject.toml b/pyproject.toml
index 4253b1dff5f..07948240e91 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -476,5 +476,7 @@ module = [
     "prodigy.components.db.*",
     "transformers.*",
     "langchain_community.*",
+    "vllm.*",
+    "numba.*",
 ]
 ignore_missing_imports = true
diff --git a/src/zenml/integrations/evidently/__init__.py b/src/zenml/integrations/evidently/__init__.py
index a87ee13b747..0d79edbfe0c 100644
--- a/src/zenml/integrations/evidently/__init__.py
+++ b/src/zenml/integrations/evidently/__init__.py
@@ -33,7 +33,7 @@
 
 # Fix numba errors in Docker and suppress logs and deprecation warning spam
 try:
-    from numba.core.errors import (  # type: ignore[import-not-found]
+    from numba.core.errors import (
         NumbaDeprecationWarning,
         NumbaPendingDeprecationWarning,
     )
diff --git a/src/zenml/integrations/vllm/services/vllm_deployment.py b/src/zenml/integrations/vllm/services/vllm_deployment.py
index d33eb22061e..d86cb3d1bbd 100644
--- a/src/zenml/integrations/vllm/services/vllm_deployment.py
+++ b/src/zenml/integrations/vllm/services/vllm_deployment.py
@@ -13,6 +13,7 @@
 #  permissions and limitations under the License.
 """Implementation of the vLLM Inference Server Service."""
 
+import argparse
 import os
 from typing import Any, List, Optional, Union
 
@@ -137,15 +138,23 @@ def run(self) -> None:
         self.endpoint.prepare_for_start()
 
         import uvloop
-        from vllm.entrypoints.openai.api_server import run_server
-        from vllm.entrypoints.openai.cli_args import make_arg_parser
-        from vllm.utils import FlexibleArgumentParser
+        from vllm.entrypoints.openai.api_server import (
+            run_server,
+        )
+        from vllm.entrypoints.openai.cli_args import (
+            make_arg_parser,
+        )
+        from vllm.utils import (
+            FlexibleArgumentParser,
+        )
 
         try:
-            parser = make_arg_parser(FlexibleArgumentParser())
-            args = parser.parse_args()
+            parser: argparse.ArgumentParser = make_arg_parser(
+                FlexibleArgumentParser()
+            )
+            args: argparse.Namespace = parser.parse_args()
             # Override port with the available port
-            self.config.port = self.endpoint.status.port
+            self.config.port = self.endpoint.status.port or self.config.port
             # Update the arguments in place
             args.__dict__.update(self.config.model_dump())
             uvloop.run(run_server(args=args))
@@ -161,7 +170,7 @@ def prediction_url(self) -> Optional[str]:
         """
         if not self.is_running:
             return None
-        return self.endpoint.prediction_url_path
+        return self.endpoint.prediction_url
 
     def predict(self, data: "Any") -> "Any":
         """Make a prediction using the service.