diff --git a/llama_stack/providers/remote/inference/vllm/vllm.py b/llama_stack/providers/remote/inference/vllm/vllm.py
index 21e4c0e1d..9e084ea30 100644
--- a/llama_stack/providers/remote/inference/vllm/vllm.py
+++ b/llama_stack/providers/remote/inference/vllm/vllm.py
@@ -9,7 +9,6 @@ from collections.abc import AsyncGenerator, AsyncIterator
 from typing import Any
 
 import httpx
-import requests
 from openai import AsyncOpenAI
 from openai.types.chat.chat_completion_chunk import (
     ChatCompletionChunk as OpenAIChatCompletionChunk,
@@ -314,14 +313,9 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
         try:
             client = self._create_client() if self.client is None else self.client
             client.models.list()  # Ensure the client is initialized
-            return HealthResponse(
-                status=HealthStatus.OK
-            )
+            return HealthResponse(status=HealthStatus.OK)
         except Exception as ex:
-            return HealthResponse(
-                status=HealthStatus.ERROR,
-                message=f"Health check failed: {str(ex)}"
-            )
+            return HealthResponse(status=HealthStatus.ERROR, message=f"Health check failed: {str(ex)}")
 
     async def _get_model(self, model_id: str) -> Model:
         if not self.model_store:
diff --git a/tests/unit/providers/inference/test_remote_vllm.py b/tests/unit/providers/inference/test_remote_vllm.py
index 375cfe82d..1fc68a631 100644
--- a/tests/unit/providers/inference/test_remote_vllm.py
+++ b/tests/unit/providers/inference/test_remote_vllm.py
@@ -653,7 +653,7 @@ async def test_health_status_success(vllm_inference_adapter):
     # Mock the client.models.list method to return successfully
     # Set vllm_inference_adapter.client to None to ensure _create_client is called
     vllm_inference_adapter.client = None
-    with patch.object(vllm_inference_adapter, '_create_client') as mock_create_client:
+    with patch.object(vllm_inference_adapter, "_create_client") as mock_create_client:
         # Create mock client and models
         mock_client = MagicMock()
         mock_models = MagicMock()
@@ -678,7 +678,7 @@ async def test_health_status_failure(vllm_inference_adapter):
     """
     vllm_inference_adapter.client = None
     # Mock the client.models.list method to raise an exception
-    with patch.object(vllm_inference_adapter, '_create_client') as mock_create_client:
+    with patch.object(vllm_inference_adapter, "_create_client") as mock_create_client:
         # Create mock client and models
         mock_client = MagicMock()
         mock_models = MagicMock()