diff --git a/llama_stack/providers/inline/inference/vllm/vllm.py b/llama_stack/providers/inline/inference/vllm/vllm.py
index c5925774b..73f7adecd 100644
--- a/llama_stack/providers/inline/inference/vllm/vllm.py
+++ b/llama_stack/providers/inline/inference/vllm/vllm.py
@@ -7,10 +7,10 @@
 import logging
 import os
 import uuid
-from typing import AsyncGenerator, Optional
+from typing import AsyncGenerator, List, Optional
 
 from llama_models.llama3.api.chat_format import ChatFormat
-from llama_models.llama3.api.datatypes import *  # noqa: F403
+
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 
@@ -18,9 +18,26 @@ from vllm.engine.arg_utils import AsyncEngineArgs
 from vllm.engine.async_llm_engine import AsyncLLMEngine
 from vllm.sampling_params import SamplingParams as VLLMSamplingParams
 
-from llama_stack.apis.inference import *  # noqa: F403
+from llama_stack.apis.common.content_types import InterleavedContent
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+    ChatCompletionResponseStreamChunk,
+    CompletionResponse,
+    CompletionResponseStreamChunk,
+    EmbeddingsResponse,
+    Inference,
+    LogProbConfig,
+    Message,
+    ResponseFormat,
+    SamplingParams,
+    ToolChoice,
+    ToolDefinition,
+    ToolPromptFormat,
+)
+from llama_stack.apis.models import Model
 
-from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
+from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.openai_compat import (
     OpenAICompatCompletionChoice,
     OpenAICompatCompletionResponse,