[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 21:01:39 +08:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions

View File

@@ -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