[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>

tests/entrypoints/openai/tool_parsers/utils.py

@@ -3,8 +3,8 @@
 
 from collections.abc import Iterable
 
-from vllm.entrypoints.openai.protocol import (
-    ChatCompletionRequest,
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.engine.protocol import (
     DeltaMessage,
     ExtractedToolCallInformation,
     FunctionCall,

tests/entrypoints/openai/utils.py

@@ -4,11 +4,13 @@ import json
 from collections.abc import AsyncGenerator
 from typing import Any
 
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionResponse,
     ChatCompletionResponseChoice,
     ChatCompletionStreamResponse,
     ChatMessage,
+)
+from vllm.entrypoints.openai.engine.protocol import (
     UsageInfo,
 )
 

tests/reasoning/test_base_thinking_reasoning_parser.py

@@ -5,7 +5,7 @@ import pytest
 from transformers import AutoTokenizer
 
 from tests.reasoning.utils import run_reasoning_extraction
-from vllm.entrypoints.openai.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
 from vllm.reasoning.basic_parsers import BaseThinkingReasoningParser
 
 

tests/reasoning/test_deepseekv3_reasoning_parser.py

@@ -4,7 +4,8 @@
 import pytest
 from transformers import AutoTokenizer
 
-from vllm.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.engine.protocol import DeltaMessage
 from vllm.reasoning.deepseek_r1_reasoning_parser import DeepSeekR1ReasoningParser
 from vllm.reasoning.deepseek_v3_reasoning_parser import DeepSeekV3ReasoningParser
 from vllm.reasoning.identity_reasoning_parser import IdentityReasoningParser

tests/reasoning/utils.py

 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
-
-from vllm.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.engine.protocol import DeltaMessage
 from vllm.reasoning import ReasoningParser
 from vllm.tokenizers.mistral import MistralTokenizer
 

tests/tool_parsers/test_ernie45_moe_tool_parser.py

@@ -7,8 +7,8 @@ from collections.abc import Generator
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import (
-    ChatCompletionRequest,
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.engine.protocol import (
     DeltaMessage,
     FunctionCall,
     ToolCall,

tests/tool_parsers/test_functiongemma_tool_parser.py

@@ -5,7 +5,7 @@ from unittest.mock import MagicMock
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
 from vllm.tool_parsers.functiongemma_tool_parser import FunctionGemmaToolParser
 
 

tests/tool_parsers/test_glm4_moe_tool_parser.py

@@ -6,7 +6,7 @@ import json
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import FunctionCall, ToolCall
+from vllm.entrypoints.openai.engine.protocol import FunctionCall, ToolCall
 from vllm.tokenizers import get_tokenizer
 from vllm.tool_parsers.glm4_moe_tool_parser import (
     Glm4MoeModelToolParser,

tests/tool_parsers/test_jamba_tool_parser.py

@@ -8,7 +8,7 @@ import partial_json_parser
 import pytest
 from partial_json_parser.core.options import Allow
 
-from vllm.entrypoints.openai.protocol import DeltaMessage, FunctionCall, ToolCall
+from vllm.entrypoints.openai.engine.protocol import DeltaMessage, FunctionCall, ToolCall
 from vllm.tokenizers import TokenizerLike, get_tokenizer
 from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
 from vllm.tool_parsers.jamba_tool_parser import JambaToolParser

tests/tool_parsers/test_kimi_k2_tool_parser.py

@@ -6,7 +6,7 @@ import json
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import FunctionCall, ToolCall
+from vllm.entrypoints.openai.engine.protocol import FunctionCall, ToolCall
 from vllm.tokenizers import get_tokenizer
 from vllm.tool_parsers.kimi_k2_tool_parser import KimiK2ToolParser
 

tests/tool_parsers/test_minimax_tool_parser.py

@@ -7,8 +7,10 @@ from typing import Any
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionToolsParam,
+)
+from vllm.entrypoints.openai.engine.protocol import (
     FunctionCall,
     ToolCall,
 )

tests/tool_parsers/test_mistral_tool_parser.py

@@ -11,7 +11,7 @@ from mistral_common.protocol.instruct.request import InstructRequest
 from mistral_common.protocol.instruct.tool_calls import FunctionCall, ToolCall
 from partial_json_parser.core.options import Allow
 
-from vllm.entrypoints.openai.protocol import DeltaMessage, DeltaToolCall
+from vllm.entrypoints.openai.engine.protocol import DeltaMessage, DeltaToolCall
 from vllm.tokenizers import TokenizerLike, get_tokenizer
 from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
 from vllm.tokenizers.mistral import MistralTokenizer

tests/tool_parsers/test_openai_tool_parser.py

@@ -14,7 +14,7 @@ from openai_harmony import (
     load_harmony_encoding,
 )
 
-from vllm.entrypoints.openai.protocol import FunctionCall, ToolCall
+from vllm.entrypoints.openai.engine.protocol import FunctionCall, ToolCall
 from vllm.tokenizers import get_tokenizer
 from vllm.tool_parsers.openai_tool_parser import OpenAIToolParser
 

tests/tool_parsers/test_qwen3coder_tool_parser.py

@@ -6,9 +6,11 @@ from collections.abc import Generator
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionRequest,
     ChatCompletionToolsParam,
+)
+from vllm.entrypoints.openai.engine.protocol import (
     DeltaMessage,
     FunctionCall,
     ToolCall,

tests/tool_parsers/test_seed_oss_tool_parser.py

@@ -7,9 +7,11 @@ from collections.abc import Generator
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionRequest,
     ChatCompletionToolsParam,
+)
+from vllm.entrypoints.openai.engine.protocol import (
     DeltaMessage,
     FunctionCall,
     ToolCall,

tests/tool_parsers/test_xlam_tool_parser.py

@@ -6,8 +6,8 @@ from collections.abc import Generator
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import (
-    ChatCompletionRequest,
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.engine.protocol import (
     DeltaMessage,
     FunctionCall,
     ToolCall,

tests/tool_use/test_chat_completion_request_validations.py

@@ -3,7 +3,7 @@
 
 import pytest
 
-from vllm.entrypoints.openai.protocol import ChatCompletionRequest
+from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
 
 
 def test_chat_completion_request_with_no_tools():

tests/tool_use/test_tool_choice_required.py

@@ -8,10 +8,10 @@ import pytest
 import regex as re
 from pydantic import TypeAdapter
 
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionToolsParam,
 )
-from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
+from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
 from vllm.tool_parsers.utils import get_json_schema_from_tools
 
 pytestmark = pytest.mark.cpu_test

tests/v1/engine/test_async_llm.py

@@ -11,12 +11,14 @@ from vllm import SamplingParams
 from vllm.assets.image import ImageAsset
 from vllm.config import VllmConfig
 from vllm.engine.arg_utils import AsyncEngineArgs
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionRequest,
     ChatCompletionResponse,
+)
+from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
+from vllm.entrypoints.openai.engine.protocol import (
     ErrorResponse,
 )
-from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
 from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
 from vllm.inputs import PromptType
 from vllm.outputs import RequestOutput

vllm/entrypoints/anthropic/serving_messages.py

@@ -25,16 +25,18 @@ from vllm.entrypoints.anthropic.protocol import (
 )
 from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
 from vllm.entrypoints.logger import RequestLogger
-from vllm.entrypoints.openai.protocol import (
+from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionNamedToolChoiceParam,
     ChatCompletionRequest,
     ChatCompletionResponse,
     ChatCompletionStreamResponse,
     ChatCompletionToolsParam,
+)
+from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
+from vllm.entrypoints.openai.engine.protocol import (
     ErrorResponse,
     StreamOptions,
 )
-from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
 from vllm.entrypoints.openai.serving_models import OpenAIServingModels
 
 logger = logging.getLogger(__name__)