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

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 13:01:39 +00:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
+6 -6
View File
@@ -22,6 +22,12 @@ from vllm.entrypoints.chat_utils import (
ChatTemplateContentFormatOption,
)
from vllm.entrypoints.constants import MCP_PREFIX
from vllm.entrypoints.openai.engine.protocol import (
FunctionCall,
ResponseInputOutputItem,
ResponseRawMessageAndToken,
ResponsesRequest,
)
from vllm.entrypoints.openai.parser.harmony_utils import (
get_encoding,
get_streamable_parser_for_assistant,
@@ -30,12 +36,6 @@ from vllm.entrypoints.openai.parser.harmony_utils import (
from vllm.entrypoints.openai.parser.responses_parser import (
get_responses_parser_for_simple_context,
)
from vllm.entrypoints.openai.protocol import (
FunctionCall,
ResponseInputOutputItem,
ResponseRawMessageAndToken,
ResponsesRequest,
)
from vllm.entrypoints.responses_utils import construct_tool_dicts
from vllm.entrypoints.tool import Tool
from vllm.entrypoints.tool_server import ToolServer