[Auto Sync] Update serving_base.py, serving_chat.py, servin... (20250910) (#10282)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: cctry <shiyang@x.ai>

python/sglang/srt/entrypoints/openai/serving_base.py

@@ -1,14 +1,18 @@
+from __future__ import annotations
+
 import json
 import logging
 import uuid
 from abc import ABC, abstractmethod
-from typing import Any, Optional, Union
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 from fastapi import HTTPException, Request
 from fastapi.responses import ORJSONResponse, StreamingResponse
 
 from sglang.srt.entrypoints.openai.protocol import ErrorResponse, OpenAIServingRequest
 from sglang.srt.managers.io_struct import GenerateReqInput
+
+if TYPE_CHECKING:
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
 
 logger = logging.getLogger(__name__)

python/sglang/srt/entrypoints/openai/serving_chat.py

@@ -1,9 +1,11 @@
+from __future__ import annotations
+
 import copy
 import json
 import logging
 import time
 import uuid
-from typing import Any, AsyncGenerator, Dict, List, Optional, Union
+from typing import TYPE_CHECKING, Any, AsyncGenerator, Dict, List, Optional, Union
 
 from fastapi import Request
 from fastapi.responses import ORJSONResponse, StreamingResponse
@@ -33,13 +35,15 @@ from sglang.srt.entrypoints.openai.utils import (
 )
 from sglang.srt.function_call.function_call_parser import FunctionCallParser
 from sglang.srt.managers.io_struct import GenerateReqInput
-from sglang.srt.managers.template_manager import TemplateManager
-from sglang.srt.managers.tokenizer_manager import TokenizerManager
 from sglang.srt.parser.conversation import generate_chat_conv
 from sglang.srt.parser.jinja_template_utils import process_content_for_template_format
 from sglang.srt.parser.reasoning_parser import ReasoningParser
 from sglang.utils import convert_json_schema_to_str
 
+if TYPE_CHECKING:
+    from sglang.srt.managers.template_manager import TemplateManager
+    from sglang.srt.managers.tokenizer_manager import TokenizerManager
+
 logger = logging.getLogger(__name__)
 
 

python/sglang/srt/entrypoints/openai/serving_completions.py

@@ -1,6 +1,8 @@
+from __future__ import annotations
+
 import logging
 import time
-from typing import Any, AsyncGenerator, Dict, List, Optional, Union
+from typing import TYPE_CHECKING, Any, AsyncGenerator, Dict, List, Optional, Union
 
 from fastapi import Request
 from fastapi.responses import ORJSONResponse, StreamingResponse
@@ -20,13 +22,15 @@ from sglang.srt.entrypoints.openai.utils import (
     to_openai_style_logprobs,
 )
 from sglang.srt.managers.io_struct import GenerateReqInput
-from sglang.srt.managers.template_manager import TemplateManager
-from sglang.srt.managers.tokenizer_manager import TokenizerManager
 from sglang.srt.parser.code_completion_parser import (
     generate_completion_prompt_from_request,
 )
 from sglang.utils import convert_json_schema_to_str
 
+if TYPE_CHECKING:
+    from sglang.srt.managers.template_manager import TemplateManager
+    from sglang.srt.managers.tokenizer_manager import TokenizerManager
+
 logger = logging.getLogger(__name__)
 
 

python/sglang/srt/entrypoints/openai/serving_embedding.py

@@ -1,4 +1,6 @@
-from typing import Any, Dict, List, Optional, Union
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
 
 from fastapi import Request
 from fastapi.responses import ORJSONResponse
@@ -13,9 +15,11 @@ from sglang.srt.entrypoints.openai.protocol import (
 )
 from sglang.srt.entrypoints.openai.serving_base import OpenAIServingBase
 from sglang.srt.managers.io_struct import EmbeddingReqInput
+from sglang.srt.parser.conversation import generate_embedding_convs
+
+if TYPE_CHECKING:
     from sglang.srt.managers.template_manager import TemplateManager
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
-from sglang.srt.parser.conversation import generate_embedding_convs
 
 
 class OpenAIServingEmbedding(OpenAIServingBase):

python/sglang/srt/entrypoints/openai/serving_responses.py

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # Adapted from vLLM's OpenAIServingResponses
 """Handler for /v1/responses requests"""
+from __future__ import annotations
 
 import asyncio
 import copy
@@ -9,7 +10,7 @@ import logging
 import time
 from contextlib import AsyncExitStack
 from http import HTTPStatus
-from typing import Any, AsyncGenerator, AsyncIterator, Optional, Union
+from typing import TYPE_CHECKING, Any, AsyncGenerator, AsyncIterator, Optional, Union
 
 import jinja2
 import openai.types.responses as openai_responses_types
@@ -54,11 +55,13 @@ from sglang.srt.entrypoints.openai.protocol import (
 from sglang.srt.entrypoints.openai.serving_chat import OpenAIServingChat
 from sglang.srt.entrypoints.openai.tool_server import MCPToolServer, ToolServer
 from sglang.srt.managers.io_struct import GenerateReqInput
-from sglang.srt.managers.template_manager import TemplateManager
-from sglang.srt.managers.tokenizer_manager import TokenizerManager
 from sglang.srt.parser.reasoning_parser import ReasoningParser
 from sglang.srt.utils import random_uuid
 
+if TYPE_CHECKING:
+    from sglang.srt.managers.template_manager import TemplateManager
+    from sglang.srt.managers.tokenizer_manager import TokenizerManager
+
 logger = logging.getLogger(__name__)