[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 -2
View File
@@ -5,13 +5,15 @@ from abc import abstractmethod
from collections.abc import Sequence
from typing import TYPE_CHECKING, Any
from vllm.entrypoints.openai.protocol import DeltaMessage
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
from vllm.reasoning.abs_reasoning_parsers import ReasoningParser
from vllm.tokenizers import TokenizerLike
if TYPE_CHECKING:
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
)
from vllm.entrypoints.openai.engine.protocol import (
ResponsesRequest,
)
else: