[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
+4 -1
View File
@@ -5,8 +5,11 @@ from collections.abc import Sequence
from transformers import PreTrainedTokenizerBase
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
)
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
from vllm.entrypoints.openai.parser.harmony_utils import parse_chat_output
from vllm.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage
from vllm.entrypoints.tool_server import ToolServer
from vllm.logger import init_logger
from vllm.reasoning import ReasoningParser